Not in the top 1,000 by GitHub stars
Flagrare/agent-skills
Claude Code skills that wrap your full dev cycle — ticket intake, ATDD planning, code review, doc-drift audits, PR writing, and changelogs.
History
Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.
View weekly changes
plugins/flagrare/skills/atdd-plan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/brag-doc/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/bug-bash/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/career/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/codebase-explore/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/daily-code-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/debug-hunt/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/design-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/editorial-pass/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/figma-matcher/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/five-lens-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/impact-scan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/impact-timeline/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/implementation-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/intake/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/interaction-polish/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/measure-impact/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/open-pr/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/opportunity-scan/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/playbook/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/pr-reviewer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/promotion/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/release-check/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/research-catalog/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/security-audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/smoke-test/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/staleness-audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/standup-report/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/tdd-writer/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/testing-philosophy/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/ticket-creator/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/tutor/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/ui-review/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/uninstall/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/update/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/ux-audit/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/visual-diff-branches/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/work-prep/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/wrap-up/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
plugins/flagrare/skills/write-docs/SKILL.md
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 0d6f99db2c7d
No earlier version was observed for comparison.
Verified commit 0d6f99db2c7da5d7df4532ca62a6ea9fb9db2ca0
git clone --filter=blob:none --no-checkout https://github.com/Flagrare/agent-skills.git .hotskills/flagrare-agent-skills && git -C .hotskills/flagrare-agent-skills checkout --detach 0d6f99db2c7da5d7df4532ca62a6ea9fb9db2ca0
# Copy each selected skill directory from .hotskills/flagrare-agent-skills into .claude/skills/<skill-name>/Heat
5.4- Star growth, last 7 daysNot available
- Star growth, last 24 hoursNot available
- Rank movement, last 7 daysNot available
- Commits, last 30 daysNot available
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekNot available
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
30-day change not yet available: not enough history.
Individual skills in this repository
- atdd-plan
plugins/flagrare/skills/atdd-plan - brag-doc
plugins/flagrare/skills/brag-doc - bug-bash
plugins/flagrare/skills/bug-bash - career
plugins/flagrare/skills/career - codebase-explore
plugins/flagrare/skills/codebase-explore - daily-code-review
plugins/flagrare/skills/daily-code-review - debug-hunt
plugins/flagrare/skills/debug-hunt - design-review
plugins/flagrare/skills/design-review - editorial-pass
plugins/flagrare/skills/editorial-pass - figma-matcher
plugins/flagrare/skills/figma-matcher - five-lens-review
plugins/flagrare/skills/five-lens-review - impact-scan
plugins/flagrare/skills/impact-scan - impact-timeline
plugins/flagrare/skills/impact-timeline - implementation-review
plugins/flagrare/skills/implementation-review - intake
plugins/flagrare/skills/intake - interaction-polish
plugins/flagrare/skills/interaction-polish - measure-impact
plugins/flagrare/skills/measure-impact - open-pr
plugins/flagrare/skills/open-pr - opportunity-scan
plugins/flagrare/skills/opportunity-scan - playbook
plugins/flagrare/skills/playbook - pr-reviewer
plugins/flagrare/skills/pr-reviewer - promotion
plugins/flagrare/skills/promotion - release-check
plugins/flagrare/skills/release-check - research-catalog
plugins/flagrare/skills/research-catalog - security-audit
plugins/flagrare/skills/security-audit - smoke-test
plugins/flagrare/skills/smoke-test - staleness-audit
plugins/flagrare/skills/staleness-audit - standup-report
plugins/flagrare/skills/standup-report - tdd-writer
plugins/flagrare/skills/tdd-writer - testing-philosophy
plugins/flagrare/skills/testing-philosophy - ticket-creator
plugins/flagrare/skills/ticket-creator - tutor
plugins/flagrare/skills/tutor - ui-review
plugins/flagrare/skills/ui-review - uninstall
plugins/flagrare/skills/uninstall - update
plugins/flagrare/skills/update - ux-audit
plugins/flagrare/skills/ux-audit - visual-diff-branches
plugins/flagrare/skills/visual-diff-branches - work-prep
plugins/flagrare/skills/work-prep - wrap-up
plugins/flagrare/skills/wrap-up - write-docs
plugins/flagrare/skills/write-docs
How it works
atdd-plan
When your agent uses it
Produce an ATDD-first implementation plan in Claude Code's native plan mode, with named design patterns called out where they earn their keep. The skill enters plan mode automatically (via the EnterPlanMode tool), runs /flagrare:codebase-explore to ground the plan in the actual codebase, then produces a plan-mode plan that MUST include both: (1) 3-5 acceptance tests in plain English defining 'done' before any implementation, written behavior-first against the public API only; and (2) any non-trivial structural decisions named as design patterns with a one-line rationale. Plan mode's native approve/edit/reject button UI is the close, ExitPlanMode is how the skill ends. Use whenever the user wants to plan a feature, fix, or refactor, 'how should we implement X', 'plan this', 'let's design X', 'where do we start on Y'. Tests follow Kent Dodds Testing Trophy: behavior over implementation, integration-heavy, public-API-only, refactor-proof. The skill stops at the plan; it does not write implementation code.
What it loads into context
Frontmatter
232 tokensAlways available to the agent
SKILL.md
2,263 tokensWhen the skill is activated
Reference documents
176,484 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The two non-negotiables
- Procedure
- Anti-patterns: refuse these
Scripts executed separately
../../hooks/measure_reminders.py../../hooks/post_skill_chain.sh../../hooks/post_skill_chain.sh../../hooks/pre_atdd_plan_gate.sh../../hooks/pre_atdd_plan_gate.sh../../hooks/research_catalog_reminder.sh../../hooks/research_catalog_reminder.sh../visual-diff-branches/references/shots.example.mjs../visual-diff-branches/scripts/capture.mjs../visual-diff-branches/scripts/compare-measures.mjs../visual-diff-branches/scripts/compose.mjs../visual-diff-branches/scripts/diff.mjs../visual-diff-branches/scripts/lib.mjs../visual-diff-branches/scripts/measure.mjs../visual-diff-branches/scripts/wait-for-rebuild.sh
Files
../../../../.claude-plugin/marketplace.jsonasset633 bytes../../.claude-plugin/plugin.jsonasset392 bytes../../hooks/hooks.jsonasset2,283 bytes../../hooks/measure_reminders.pyruns8,809 bytes../../hooks/post_skill_chain.shruns1,096 bytes../../hooks/post_skill_chain.shruns1,096 bytes../../hooks/pre_atdd_plan_gate.shruns890 bytes../../hooks/pre_atdd_plan_gate.shruns890 bytes../../hooks/research_catalog_reminder.shruns925 bytes../../hooks/research_catalog_reminder.shruns925 bytesSKILL.mdcore10,085 bytes../brag-doc/SKILL.mddoc28,538 bytes../bug-bash/SKILL.mddoc20,777 bytes../bug-bash/evals/evals.jsonasset2,683 bytes../bug-bash/evals/evals.jsonasset2,683 bytes../bug-bash/evals/evals.jsonasset2,683 bytes../bug-bash/references/backend.mddoc9,187 bytes../bug-bash/references/exploratory.mddoc11,213 bytes../bug-bash/references/ui.mddoc8,526 bytes../career/SKILL.mddoc12,099 bytes../career/evals/evals.jsonasset2,321 bytes../career/evals/fixtures/config.jsonasset819 bytes../career/evals/fixtures/contributions.log.mddoc494 bytes../career/evals/fixtures/flags.jsonasset168 bytes../career/evals/fixtures/initiatives.jsonasset898 bytes../career/evals/fixtures/opportunity-state.jsonasset31 bytes../career/evals/fixtures/promotion-map.jsonasset3,777 bytes../codebase-explore/SKILL.mddoc4,885 bytes../daily-code-review/SKILL.mddoc8,612 bytes../debug-hunt/SKILL.mddoc9,734 bytes../debug-hunt/evals/evals.jsonasset1,680 bytes../design-review/SKILL.mddoc11,210 bytes../design-review/references/critique-and-anti-patterns.mddoc6,356 bytes../design-review/references/principles.mddoc8,099 bytes../design-review/references/tactics.mddoc8,119 bytes../editorial-pass/SKILL.mddoc18,790 bytes../figma-matcher/SKILL.mddoc17,651 bytes../five-lens-review/SKILL.mddoc12,178 bytes../impact-scan/SKILL.mddoc40,984 bytes../impact-scan/evals/evals.jsonasset3,514 bytes../impact-scan/evals/fixtures/initiatives.jsonasset229 bytes../impact-scan/evals/fixtures/own-work-items.jsonasset1,148 bytes../impact-scan/evals/fixtures/promotion-map.jsonasset2,090 bytes../impact-timeline/SKILL.mddoc11,440 bytes../impact-timeline/references/playbook.mddoc6,779 bytes../implementation-review/SKILL.mddoc17,388 bytes../intake/SKILL.mddoc18,330 bytes../interaction-polish/SKILL.mddoc9,540 bytes../interaction-polish/references/accessibility-performance.mddoc6,053 bytes../interaction-polish/references/easing-springs-timing.mddoc6,292 bytes../interaction-polish/references/patterns.mddoc7,525 bytes../measure-impact/SKILL.mddoc11,641 bytes../measure-impact/evals/evals.jsonasset2,602 bytes../measure-impact/evals/evals.jsonasset2,602 bytes../measure-impact/evals/fixtures/config.jsonasset147 bytes../measure-impact/evals/fixtures/contributions.log.mddoc290 bytes../measure-impact/evals/fixtures/measurements.jsonasset995 bytes../open-pr/SKILL.mddoc15,508 bytes../opportunity-scan/SKILL.mddoc22,464 bytes../opportunity-scan/evals/evals.jsonasset3,850 bytes../opportunity-scan/evals/fixtures/config.jsonasset819 bytes../opportunity-scan/evals/fixtures/initiatives-with-active.jsonasset1,373 bytes../opportunity-scan/evals/fixtures/initiatives.jsonasset311 bytes../opportunity-scan/evals/fixtures/promotion-map.jsonasset5,256 bytes../playbook/SKILL.mddoc8,343 bytes../pr-reviewer/SKILL.mddoc34,849 bytes../promotion/SKILL.mddoc16,245 bytes../promotion/evals/evals.jsonasset1,722 bytes../promotion/reference/map-schema.mddoc3,475 bytes../promotion/reference/map-template.mddoc1,929 bytes../release-check/SKILL.mddoc24,359 bytes../research-catalog/SKILL.mddoc9,816 bytes../security-audit/SKILL.mddoc12,270 bytes../smoke-test/SKILL.mddoc11,226 bytes../smoke-test/references/backend.mddoc11,688 bytes../smoke-test/references/ui.mddoc9,128 bytes../staleness-audit/SKILL.mddoc10,812 bytes../standup-report/SKILL.mddoc32,930 bytes../tdd-writer/SKILL.mddoc21,425 bytes../testing-philosophy/SKILL.mddoc7,753 bytes../ticket-creator/SKILL.mddoc31,904 bytes../tutor/SKILL.mddoc17,190 bytes../ui-review/SKILL.mddoc14,496 bytes../ui-review/references/demo-video.mddoc5,715 bytes../uninstall/SKILL.mddoc1,009 bytes../update/SKILL.mddoc1,299 bytes../ux-audit/SKILL.mddoc20,488 bytes../ux-audit/references/finding-triggers.mddoc9,357 bytes../ux-audit/references/findings-template.mddoc3,210 bytes../ux-audit/references/severity-rubric.mddoc3,816 bytes../visual-diff-branches/SKILL.mddoc8,063 bytes../visual-diff-branches/references/config.mddoc2,545 bytes../visual-diff-branches/references/shots.example.mjsruns3,804 bytes../visual-diff-branches/scripts/capture.mjsruns2,325 bytes../visual-diff-branches/scripts/compare-measures.mjsruns1,577 bytes../visual-diff-branches/scripts/compose.mjsruns2,557 bytes../visual-diff-branches/scripts/diff.mjsruns3,198 bytes../visual-diff-branches/scripts/lib.mjsruns1,525 bytes../visual-diff-branches/scripts/measure.mjsruns2,514 bytes../visual-diff-branches/scripts/wait-for-rebuild.shruns1,172 bytes../work-prep/SKILL.mddoc8,314 bytes../wrap-up/SKILL.mddoc9,307 bytes../write-docs/SKILL.mddoc28,487 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbrag-doc
When your agent uses it
Generate a comprehensive, impact-framed brag-doc entry for a chosen time window (day, week, biweek, month, or custom). Pulls authored PRs, reviews given, commits, deploys, and linked tickets across GitHub, local git, and configured MCPs, then synthesises a themed narrative, leading with outcomes, quantifying impact, owning the work in first-person past tense, separating IC contributions from amplification, and naming the judgment exercised. Output is designed to drop straight into a developer journal, a personal bragging sheet, or a performance-review packet. Accepts a mode argument, `/flagrare:brag-doc resumancer` renders the output as ready-to-paste Resumancer CLI commands (`resumancer impact "..." --branch ...`) instead of markdown. Use whenever the user says "brag doc", "brag sheet", "what did I do this week", "weekly recap", "monthly recap", "performance review prep", "what should I tell my manager", "summarise my impact", "career log entry", "give me my wins", "biweekly recap", or any variant about looking back over a longer window than a single day's standup. Also trigger near review season ("self-review", "perf packet", "evaluation prep"), and on phrases like "log my wins to resumancer" or "make resumancer entries for this week" (which should pass the `resumancer` mode). For windows longer than about a month, a tenure retrospective, a departure record, or "everything I did at this company", hand off to `/flagrare:impact-timeline` instead; this skill's window tops out at a month.
What it loads into context
Frontmatter
352 tokensAlways available to the agent
SKILL.md
6,919 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Modes
- Setup (first run only)
- Resolve the time window
- Data collection
- Naming work in human terms
- Synthesis: the brag-doc voice
- Output format
- Rendering by mode
- Edge cases
- Output
Files
SKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytesSKILL.mdcore28,538 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubbug-bash
When your agent uses it
Programmatic bug bashing, ingest a prescribed test plan (Notion, markdown, pasted spec), drive a real running system (browser via Chrome DevTools / Playwright MCP, backend via API tools when relevant), run every prescribed case with evidence, then do exploratory passes (viewports, edge inputs, multi-actor flows, codebase-driven concerns, additional context like meeting transcripts, emails and links checked in the real inbox with a control case, other languages, failures and races) without ever claiming a bug it didn't itself reproduce. Fills free-text fields with tagged, playful test data that also probes something (unicode, HTML, template syntax, length). Lands results in a local MD file by default, optionally writes back to the source (Notion bug DB, test case Eng QA columns, etc.) in the user's voice. Use whenever the user says 'bug bash', 'QA this feature', 'run the test cases', 'go through this test plan', 'verify these scenarios', 'do a bash on X', when they hand over a Notion test case page, or any time programmatic end-to-end verification of a feature against a checklist is needed. Also use it when a smoke test passed but the user wants more cases tested, or asks 'what else should we test' and then 'test it yourself'. Make sure to use this skill even when the user just says 'test this Notion page' or 'check these scenarios', anything that smells like running someone else's prescribed test plan against a live system.
What it loads into context
Frontmatter
316 tokensAlways available to the agent
SKILL.md
4,657 tokensWhen the skill is activated
Reference documents
8,461 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this exists
- Step 1: Lock the goal explicitly
- Step 2: Ingest the test plan
- Step 3: Detect the target environment
- Step 4: Prepare the environment
- Step 5: Strict pass: run the prescribed cases
- Step 6: Exploratory pass
- Step 7: Land the results
- Step 8: Confirm goal met
- Anti-patterns
- Flow position
- References
Files
../../../../docs/research/2026-06-11-claude-code-goal-anti-stall.mddoc8,314 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesSKILL.mdcore20,777 bytesevals/evals.jsonasset2,683 bytesreferences/backend.mddoc9,187 bytesreferences/exploratory.mddoc11,213 bytesreferences/ui.mddoc8,526 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcareer
When your agent uses it
Run the career skills that are due, in one pass, and return one short combined digest plus an updated board. It reads timestamps and flags to decide: the promotion map's first run when there is none (after asking), a refresh of map sections that are older than 90 days or flagged by a scan, an opportunity scan when the last one is a month old, and an impact scan every time. The digest leads with the initiative the user owns and its next step, then up to 5 threads worth weighing in on, one line on the promotion map (open rubric rows, people who haven't seen the work, when to talk to the manager, the packet deadline), anything that needs the user, and an "all answering, nothing owned" warning when the user keeps replying but owns nothing. A scheduled run (from /loop or a schedule) never asks questions and never posts; it lists what needs the user as pending. Use when the user says "career", "career check", "career digest", "run my career skills", "what should I do for my promotion this week", "daily career scan", or sets up a recurring career run. Also trigger for a scheduled career run.
What it loads into context
Frontmatter
248 tokensAlways available to the agent
SKILL.md
2,880 tokensWhen the skill is activated
Reference documents
123 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Library
- Interactive or scheduled
- Workflow
- Setting up a recurring run
Files
SKILL.mdcore12,099 bytesevals/evals.jsonasset2,321 bytesevals/fixtures/config.jsonasset819 bytesevals/fixtures/contributions.log.mddoc494 bytesevals/fixtures/flags.jsonasset168 bytesevals/fixtures/initiatives.jsonasset898 bytesevals/fixtures/opportunity-state.jsonasset31 bytesevals/fixtures/promotion-map.jsonasset3,777 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubcodebase-explore
When your agent uses it
Explore the codebase to map conventions, reusable utilities, analogous features, and data flows relevant to a planned change. Returns raw findings (file paths, patterns, code snippets), does NOT produce a plan. Used by /flagrare:atdd-plan as its codebase understanding step.
What it loads into context
Frontmatter
68 tokensAlways available to the agent
SKILL.md
1,092 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Inputs
- Step 1: Check for prior attempts
- Step 2: Identify the feature area
- Step 3: Find analogous features
- Step 4: Map conventions
- Step 5: Inventory reusable pieces
- Step 6: Check constraints
- Output Format
- Anti-patterns
- Flow position
Files
SKILL.mdcore4,885 bytesSKILL.mdcore4,885 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdaily-code-review
When your agent uses it
Generate a daily code review report showing stale PRs, items needing your attention, and active work for your team. Use whenever the user asks for a PR report, code review status, daily standup prep, team PR overview, "what needs review", "what's stale", "show me open PRs", "daily review", "PR check", "review report", "what should I look at today", or any question about tracking pull request activity across a team or pod. Also trigger when the user mentions a specific pod name that matches a saved config.
What it loads into context
Frontmatter
121 tokensAlways available to the agent
SKILL.md
2,201 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Setup (first run only)
- Detect "Me"
- Data Collection
- Classification
- Report Format
- Output
- Edge cases
Files
SKILL.mdcore8,612 bytesSKILL.mdcore8,612 bytesSKILL.mdcore8,612 bytesSKILL.mdcore8,612 bytesSKILL.mdcore8,612 bytesSKILL.mdcore8,612 bytesSKILL.mdcore8,612 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdebug-hunt
When your agent uses it
Evidence-first debugging for bugs that are hard to reproduce, intermittent, performance-related, or where previous static-analysis fixes have failed. Declares an explicit goal via /goal (the bug no longer reproduces), then loops through Hypothesis → Instrument → Reproduce → Analyze → Fix until that goal is met. Uses ATDD via /flagrare:atdd-plan to write the fix when the codebase has tests. Triggers when the user reports a difficult bug, says 'this only happens sometimes', 'my fix didn't work', 'I can't reproduce this consistently', 'what's causing this crash', 'hunt this bug down', 'there's a weird bug', 'something is broken intermittently', 'debug-hunt', or describes runtime behaviour that diverges from what the code says should happen.
What it loads into context
Frontmatter
170 tokensAlways available to the agent
SKILL.md
2,093 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 0: Set the goal
- Phase 1: Context & Hypotheses
- Phase 2: Pattern Analysis
- Phase 3: Instrumentation
- Phase 4: Reproduction & Analysis
- Phase 5: Resolution
- Phase 6: Verify & Cleanup
- Exit condition
- Anti-patterns
Files
SKILL.mdcore9,734 bytesevals/evals.jsonasset1,680 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubdesign-review
When your agent uses it
Evaluate and refine UI the way a senior product designer would, visual hierarchy, spacing and rhythm, typographic scale, legibility, information density, alignment, and restraint, then apply the highest-leverage fixes. Use this skill WHENEVER the user says a UI / page / screen / component feels 'clunky', 'packed', 'cramped', 'busy', 'off', 'amateur', 'cluttered', or 'needs polish'; when they ask to 'improve the design / layout / hierarchy / spacing / legibility', 'make this look designed / professional', 'apply design principles', 'clean this up', 'review the design', or want a 'senior designer' / 'senior product designer' pass; and proactively after building any non-trivial UI, to critique and tighten it before moving on. Grounded in the design canon (Dieter Rams, Edward Tufte, the Gestalt principles, the Vignelli Canon, Nielsen's heuristics) and the Refactoring UI playbook. It respects and extends the project's existing brand / design system first, runs a mandatory system coverage inventory (undesigned groups and unspent brand personality are automatic findings, not just visual excess), reviews the whole surface across all states rather than the recent diff, and documents any missing pattern before building it. When a screen 'lacks personality' it benchmarks named personality-forward references (e.g. PostHog, Duolingo) and designs from them rather than rearranging what exists. Works on existing UI code (improves it in place) or on a screenshot / description. Distinct from a usability/UX audit (this is visual / product-design craft) and from code review (this is design, not correctness).
What it loads into context
Frontmatter
361 tokensAlways available to the agent
SKILL.md
2,669 tokensWhen the skill is activated
Reference documents
5,502 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The one move: emphasize by de-emphasizing
- First, respect the design system
- Called by `/flagrare:ui-review`
- Workflow: diagnose, then apply
- The lenses (condensed, depth in `references/`)
- References, read the relevant one when you need depth
Files
SKILL.mdcore11,210 bytesSKILL.mdcore11,210 bytesreferences/critique-and-anti-patterns.mddoc6,356 bytesreferences/principles.mddoc8,099 bytesreferences/tactics.mddoc8,119 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubeditorial-pass
When your agent uses it
Review a finished or near-finished document the way a human editor reads it, start to finish, building a model of what it's trying to communicate, then diagnosing cohesion, coherence, narrative throughline, pacing, consistency, reading fluency, contextualization, clarity, and illustration (is every named screen and system linked and shown) across the whole piece, never just line-by-line. Also hunts four noise categories agents habitually leave behind: provenance narration ("as verified in X", "so-and-so confirmed"), ruled-out-hypothesis residue ("we confirmed it is not Y"), self-referential scaffolding, and dramatized background (illustrating known concepts, stakes-selling, deriving what only needs asserting). Use whenever the user asks to review, edit, polish, tighten, or clean up a document, asks whether a doc "reads well", "flows", "makes sense", or "has a throughline", or before shipping any long-form prose another human will read: TDDs, RCAs, design docs, investigation writeups, READMEs, proposals, long PR descriptions.
What it loads into context
Frontmatter
227 tokensAlways available to the agent
SKILL.md
4,008 tokensWhen the skill is activated
Reference documents
1,293 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- The procedure
- Anti-patterns
- Cross-references
- Why this exists
Files
../../../../docs/research/2026-07-03-editorial-pass-prior-art.mddoc5,679 bytesSKILL.mdcore18,790 bytesSKILL.mdcore18,790 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfigma-matcher
When your agent uses it
Enforces pixel-perfect implementation of Figma designs by exhaustively extracting every visual property from Figma, spinning up Chrome DevTools to measure the current implementation, building a full comparison checklist, and fixing all discrepancies in a single pass. MUST be triggered whenever implementing UI from Figma, fixing styling to match Figma, or any time the user says "match Figma", "check against Figma", "compare to design", "the design doesn't match", "colors are wrong", "spacing is off", or references a Figma URL in a styling context. Also trigger when you just finished writing CSS/styling code that was informed by a Figma design. This skill is NON-OPTIONAL when Figma designs are involved in styling work.
What it loads into context
Frontmatter
159 tokensAlways available to the agent
SKILL.md
4,197 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why This Exists
- HARD GATE
- The Process
- Rules
- When This Skill Applies
- Output Format
Files
SKILL.mdcore17,651 bytesSKILL.mdcore17,651 bytesSKILL.mdcore17,651 bytesSKILL.mdcore17,651 bytesSKILL.mdcore17,651 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubfive-lens-review
When your agent uses it
Evaluate a product-direction question through five expert lenses, Senior PM, Senior Product Engineer, Senior Product Designer, Senior Design Engineer, and a realistic end user, then synthesize the conclusions into a single recommendation. Use whenever a user-facing decision has multiple competing constraints (lifecycle behavior, data-model trade-offs, destructive actions, UX choices that touch retention) and a one-perspective answer would miss something. Trigger phrases: 'what should we do about X', 'what happens when the user Y', 'how should we handle this case', 'I need to think through this', 'help me decide', 'we don't have answers for these questions', 'spawn personas', 'evaluate from all POVs'. Especially use this when the user is mid-implementation and surfaces an edge case the spec didn't cover, that's when single-perspective reasoning silently locks in the wrong default.
What it loads into context
Frontmatter
183 tokensAlways available to the agent
SKILL.md
2,538 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When this skill is the right tool
- Step 1: Frame the decision precisely
- Step 2: Spawn five subagents in parallel
- Step 3: Wait for all five, then synthesize
- Step 4: Present back as written prose, not bullet salad
- Fallback when parallel dispatch isn't available
- Anti-patterns: refuse these
- The cost-benefit honest take
Files
SKILL.mdcore12,178 bytesSKILL.mdcore12,178 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubimpact-scan
When your agent uses it
Scan the org's communication surfaces (chat like Slack or Teams, open PRs, RFC docs and design docs, ticket threads, whichever MCPs are connected) for high-leverage discussions the user should weigh in on, decisions still being formed, people stuck or circling, questions squarely inside the user's domains, cross-team changes touching systems they own or depend on. Built for engineers working toward promotion, it hunts opportunities to operate at the next level (influence beyond assigned work), ranks them by leverage and credibility, drafts replies in the user's own voice for approval, and logs posted contributions as promotion evidence that /flagrare:brag-doc can later consume. Use whenever the user says "impact scan", "senior scan", "promo scan", "what needs my attention", "where should I weigh in", "anything I should jump into", "scan slack", "scan PRs", "catch me up on what's happening", or any variant of "where can I have the most impact today", even when the skill isn't named. Also trigger when the user talks about wanting more visibility, more scope, or operating above their level. Also trigger when the user pastes a message starting with "Board:" (copied from the Career Board's Tell Claude buttons): it says what changed on a board item, and this skill updates the board.
What it loads into context
Frontmatter
280 tokensAlways available to the agent
SKILL.md
9,721 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Surfaces
- Setup and state (every run)
- Workflow
Files
SKILL.mdcore40,984 bytesSKILL.mdcore40,984 bytesSKILL.mdcore40,984 bytesSKILL.mdcore40,984 bytesevals/evals.jsonasset3,514 bytesevals/fixtures/initiatives.jsonasset229 bytesevals/fixtures/own-work-items.jsonasset1,148 bytesevals/fixtures/promotion-map.jsonasset2,090 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubimpact-timeline
When your agent uses it
Build a month-by-month career impact timeline across an entire tenure (or any multi-month window), sweeping every available source (GitHub, issue tracker, Slack, Notion, meeting notes like Granola, the company BI/data platform, Datadog, Sentry) one month at a time, then attaching real product/technical/business metrics to every entry in "accomplished X, measured by Y, by doing Z" form. Use this whenever the user wants a tenure retrospective, a departure/offboarding impact record, "everything I did at this company", a promotion or performance-review packet covering many months, a year-in-review, or asks to add metrics/evidence to an existing career document. For a single day/week/month recap, use `/flagrare:standup-report` or `/flagrare:brag-doc` instead; this skill is for the long arc.
What it loads into context
Frontmatter
187 tokensAlways available to the agent
SKILL.md
2,537 tokensWhen the skill is activated
Reference documents
1,601 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Phase 0: Setup and identity
- Phase 1: Bulk enumeration (once, up front)
- Phase 2: Month loop
- Phase 3: Meeting-notes sweep
- Phase 4: Metrics pass
- Phase 5: Synthesis
- Single-month or short-window invocations
- Refreshing an existing timeline
Files
SKILL.mdcore11,440 bytesSKILL.mdcore11,440 bytesSKILL.mdcore11,440 bytesSKILL.mdcore11,440 bytesSKILL.mdcore11,440 bytesreferences/playbook.mddoc6,779 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubimplementation-review
When your agent uses it
Pre-commit quality gate. Invoke before every git commit, after /flagrare:staleness-audit. Seven checks, plan gaps, use-case coverage gaps, missing test scenarios, test philosophy violations (Kent Dodds Testing Trophy), SOLID violations, Clean Code violations, and security vulnerabilities. Each check is delegated to a parallel subagent. Surfaces findings before they land in history. Also invoke when the user says review this, am I done, did I miss anything, or check the quality.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
4,016 tokensWhen the skill is activated
Reference documents
4,917 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Gather inputs (main agent)
- Step 2: Dispatch seven subagents in parallel
- Step 3: Synthesise (main agent)
- Commit-flow position
- Anti-patterns
Files
../../../../docs/research/2026-09-14-open-code-review-teardown.mddoc22,509 bytesSKILL.mdcore17,388 bytesSKILL.mdcore17,388 bytesSKILL.mdcore17,388 bytesSKILL.mdcore17,388 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubintake
When your agent uses it
Pre-planning ticket ingestion. Given a ticket ID or URL, reads the full ticket via MCP or CLI, follows all referenced links (Notion, Figma, GitHub, articles, etc.) using parallel subagents, synthesises a context brief, grounds it in the actual codebase via /flagrare:codebase-explore, then asks codebase-informed clarifying questions before handing off to /flagrare:atdd-plan. Works with Linear, Jira, Asana, Shortcut, Trello.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
4,372 tokensWhen the skill is activated
Reference documents
1,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Lock the goal first (anti-stall): do this before Step 0
- Step 0: Inventory available tools
- Step 1: Parse the input
- Step 2: Read the ticket
- Step 3: Follow all references in parallel
- Step 4: Synthesise the context brief (without questions yet)
- Step 4.5: Ground the brief in the codebase
- Step 5: Ask codebase-informed clarifying questions
- Step 6: Present overview and prompt for next step
- Anti-patterns
- Flow position
Files
../../../../docs/research/2026-06-11-claude-code-goal-anti-stall.mddoc8,314 bytesSKILL.mdcore18,330 bytesSKILL.mdcore18,330 bytesSKILL.mdcore18,330 bytesSKILL.mdcore18,330 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubinteraction-polish
When your agent uses it
Elevate the feel, polish, and 'juice' of UI interactions and animations, in the craft tradition of Emil Kowalski (sonner, vaul) and Josh Comeau. Apply it WHENEVER the user wants an interface to feel better, smoother, more polished, responsive, satisfying, delightful, or 'alive'; when they say an interaction feels stiff, janky, dead, cheap, flat, or off; when they mention adding animation, motion, micro-interactions, springs, transitions, easing, or hover/press effects; or when they ask to 'add juice', 'make it feel good', 'make it satisfying', or 'polish' a button, modal, toast, drawer, toggle, menu, list, or page transition. Works on existing components (improves them in place) or a described interaction (builds it), CSS-first and adapting to the project's stack, with accessibility (prefers-reduced-motion) and performance (compositor-only) built in, and the taste to know when NOT to animate. Trigger phrases: 'make this feel nicer', 'add some juice', 'this feels stiff', 'this feels janky', 'polish this interaction', 'make it satisfying', 'improve the animation', 'it feels cheap', 'make it more delightful', 'give it some life'.
What it loads into context
Frontmatter
282 tokensAlways available to the agent
SKILL.md
2,285 tokensWhen the skill is activated
Reference documents
4,975 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The one idea: feedback, not decoration
- First, do no harm
- Called by `/flagrare:ui-review`
- Workflow
- The core toolkit (condensed, deep tables in `references/`)
- When the input is a description (no code yet)
- References
Files
SKILL.mdcore9,540 bytesreferences/accessibility-performance.mddoc6,053 bytesreferences/easing-springs-timing.mddoc6,292 bytesreferences/patterns.mddoc7,525 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubmeasure-impact
When your agent uses it
Measure the impact of a piece of the user's work in a systematic way, at any stage. Before building, it makes an educated guess (a "bet"): a measured baseline, the closest comparable that can be measured, scaled by the right base, a range, a confidence level, and the saved query that will measure it. After launch, it re-runs that same query and gives a verdict (worked, didn't work, can't tell). For work already shipped, it finds the best number still available or says honestly that none exists. Every result is written as action, measured result, impact, for the user's written case and for sharing. Use when the user says "measure impact", "what impact did this have", "how will we know this worked", "set a bet", "success metric", "shipped", "launched", "self-review", "brag", or when another flagrare skill hands off with "called by". Do not use for small fixes with no user-visible change: record a skip instead.
What it loads into context
Frontmatter
215 tokensAlways available to the agent
SKILL.md
2,811 tokensWhen the skill is activated
Reference documents
80 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Library
- Stages
- The method, every time
- Confidence levels
- Verdicts after launch
- Output
- Reminders
- Rules
- Credits
Files
SKILL.mdcore11,641 bytesSKILL.mdcore11,641 bytesSKILL.mdcore11,641 bytesSKILL.mdcore11,641 bytesSKILL.mdcore11,641 bytesSKILL.mdcore11,641 bytesSKILL.mdcore11,641 bytesevals/evals.jsonasset2,602 bytesevals/fixtures/config.jsonasset147 bytesevals/fixtures/contributions.log.mddoc290 bytesevals/fixtures/measurements.jsonasset995 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubopen-pr
When your agent uses it
Open a pull request that follows the repo's conventions. Reads the PR template from .github/PULL_REQUEST_TEMPLATE.md, fills it with contextualized content (not enumerations), links tracker tickets, writes testing notes, and uses /flagrare:write-docs style for the description. Use when the user says 'open a pr', 'create pr', 'push and pr', 'submit this', 'open pull request', or any variation. Also triggers when code is ready to ship and the user wants to get it reviewed.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
3,559 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Workflow
- Writing style for PR descriptions
- Anti-patterns
- Flow position
Files
SKILL.mdcore15,508 bytesSKILL.mdcore15,508 bytesSKILL.mdcore15,508 bytesSKILL.mdcore15,508 bytesSKILL.mdcore15,508 bytesSKILL.mdcore15,508 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubopportunity-scan
When your agent uses it
Propose two or three pieces of work the user could own end to end, instead of threads to reply to. It starts from the metrics leadership watches (themes, OKRs, planning docs, meeting notes such as Granola), then sweeps the org's connected surfaces (chat, tickets, docs, PRs, meeting notes) over the last month for recurring pain, silent degradation, ownership gaps, unanswered invitations, metric gaps and leadership priorities, adds the problems /flagrare:impact-scan handed off, checks that nobody already owns each one, keeps only work that moves a named metric and that the user's seat can move, and ranks it by impact and against the user's promotion map (what they want more and less of, which open rubric row it closes, who cares and whether they have seen the user's work, whether it can land before the target cycle). Each proposal comes with evidence links, a hypothesis and success metric set before building, the smallest first step, and a short pitch for the manager that fits how the company decides. Keeps at most one initiative active, and only after manager alignment. Runs about monthly. Use when the user says "opportunity scan", "what should I own", "what could I lead", "find me a project", "what problem should I pick up", "what would move the needle", "I want to own something end to end", or asks for work that would show next-level scope. Also trigger from /flagrare:career when the scan is due.
What it loads into context
Frontmatter
314 tokensAlways available to the agent
SKILL.md
5,332 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Library and state
- Setup (every run)
- Workflow
Files
SKILL.mdcore22,464 bytesevals/evals.jsonasset3,850 bytesevals/fixtures/config.jsonasset819 bytesevals/fixtures/initiatives-with-active.jsonasset1,373 bytesevals/fixtures/initiatives.jsonasset311 bytesevals/fixtures/promotion-map.jsonasset5,256 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubplaybook
When your agent uses it
Write a playbook, a step-by-step tutorial that a non-engineer follows to use an internal tool or run an operational process (launch agents placing test orders, support agents refunding, ops checking a dashboard). It runs the real flow in dev for screenshots, quotes the UI's exact messages from the code, links every page, channel, account and dashboard it names, finds escalation paths from past Slack threads instead of asking, and writes in tutorial shape (numbered steps, one action per line, "If it says / Do this" tables), not prose. Use when the user says "write a playbook", "runbook", "guide for <team>", "how-to for agents", "training doc", or "document how to use <tool> for ops/support/launch". Not for engineering docs, TDDs or READMEs: those are /flagrare:write-docs and /flagrare:tdd-writer.
What it loads into context
Frontmatter
200 tokensAlways available to the agent
SKILL.md
1,958 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The shape
- Get the facts from the source
- Screenshots
- Open decisions
- Publishing
- Self-check before handing over
- Cross-references
Files
SKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytesSKILL.mdcore8,343 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpr-reviewer
When your agent uses it
Review pull requests with full context. Fetches linked Jira tickets, Figma designs, and Notion docs via MCP, spawns parallel subagents for systematic code review (correctness, security, tests, SOLID, clean code), then drafts friendly, humanized GitHub-ready comments. Use when reviewing PRs, examining code changes, or when the user asks for a code review.
What it loads into context
Frontmatter
87 tokensAlways available to the agent
SKILL.md
8,117 tokensWhen the skill is activated
Reference documents
4,917 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Anti-patterns
- Flow position
Files
../../../../docs/research/2026-09-14-open-code-review-teardown.mddoc22,509 bytesSKILL.mdcore34,849 bytesSKILL.mdcore34,849 bytesSKILL.mdcore34,849 bytesSKILL.mdcore34,849 bytesSKILL.mdcore34,849 bytesSKILL.mdcore34,849 bytesSKILL.mdcore34,849 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubpromotion
When your agent uses it
Build and maintain a sourced promotion map for the user's next level. It interviews the user about their target (level, track, cycle, and why), researches how promotions actually work at their company (process, calendar, packet template, the rubric managers rate against), maps the org and who has first-hand knowledge of the user's work, and computes when to talk to their manager. Every fact carries a source and a verified/unverified/inferred status, and conflicting sources are shown, not resolved silently. Writes ~/.claude/skills/flagrare/career/promotion-map.md and .json, which impact-scan, opportunity-scan and career read. Use when the user says "promotion", "promo plan", "how do promotions work here", "when should I talk to my manager about promotion", "who should see my work", "am I ready for senior", "build my promotion map", or "promotion packet" (packet mode). Also trigger when the user asks about career strategy, sponsors, or calibration at their company.
What it loads into context
Frontmatter
213 tokensAlways available to the agent
SKILL.md
3,813 tokensWhen the skill is activated
Reference documents
1,423 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Library
- 1. Load state (every run)
- 2. Rules for every fact
- 3. First run
- 4. Refresh
- 5. Packet mode (`/flagrare:promotion packet`)
Files
SKILL.mdcore16,245 bytesSKILL.mdcore16,245 bytesSKILL.mdcore16,245 bytesevals/evals.jsonasset1,722 bytesreference/map-schema.mddoc3,475 bytesreference/map-template.mddoc1,929 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubrelease-check
When your agent uses it
Post-commit gate. Invoke after every commit (right after /flagrare:staleness-audit). Checks whether a release is due, and if so, proposes a semver bump and a value-focused CHANGELOG entry modeled on Valve's Dota 2 patch notes, describing what the user gains, never what was refactored. Acts on approval.
What it loads into context
Frontmatter
81 tokensAlways available to the agent
SKILL.md
6,081 tokensWhen the skill is activated
Reference documents
1,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- Procedure
- Anti-patterns
- Cross-references
- Why this exists
Files
../../../../docs/research/2026-06-11-claude-code-goal-anti-stall.mddoc8,314 bytesSKILL.mdcore24,359 bytesSKILL.mdcore24,359 bytesSKILL.mdcore24,359 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubresearch-catalog
When your agent uses it
Whenever you do real external research (WebFetch, WebSearch, or Explore-agent fetches of URLs outside the repo), catalog it in docs/research/ before sending the synthesis back to the user. Credits the sources, captures the findings, and creates a traceable link from the decision back to the evidence.
What it loads into context
Frontmatter
70 tokensAlways available to the agent
SKILL.md
2,288 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- Procedure
- File template
- Index template (for `docs/research/README.md`)
- Style rules for entries
- Anti-patterns
- Cross-references
Files
SKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytesSKILL.mdcore9,816 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsecurity-audit
When your agent uses it
Focused security review of a change. Finds HIGH-CONFIDENCE, concretely exploitable vulnerabilities in the staged diff (injection, broken authn/authz, secrets and data exposure, unsafe deserialization, crypto misuse, SSRF) and audits dependencies when a lockfile moved, using the repo's own package manager. Runs as Check 7 of /flagrare:implementation-review, and standalone when the user says 'security review', 'security audit', 'check this for vulnerabilities', 'is this safe', 'any security holes', 'threat check', or before shipping anything that touches auth, user input, secrets, or untrusted data. Reports only findings with a concrete exploit path, never theoretical noise.
What it loads into context
Frontmatter
153 tokensAlways available to the agent
SKILL.md
2,812 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The one rule that matters
- What to examine
- Methodology
- Dependency audit
- False-positive precedents
- Output format
- Flow position
- Anti-patterns
Files
SKILL.mdcore12,270 bytesSKILL.mdcore12,270 bytesSKILL.mdcore12,270 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubsmoke-test
When your agent uses it
Goal-driven smoke test for the feature just implemented. Drives a browser (UI) or hits the running service (backend), both, when full-stack. Tests every behaviour acceptance criteria define plus exploratory edges, catches console errors / network failures / a11y issues / contract violations / auth leaks / missing observability, fixes every gap or bug it finds, then re-runs until clean. Captures the successful trajectory as a permanent test before declaring done. Use after implementation and after figma-matcher (when UI), before /flagrare:wrap-up. Triggers when the user says 'smoke test', 'does this actually work', 'test the feature', 'validate this', 'launch the app and test', 'make sure nothing is broken', or finishes implementing a feature.
What it loads into context
Frontmatter
166 tokensAlways available to the agent
SKILL.md
2,546 tokensWhen the skill is activated
Reference documents
4,729 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this exists
- Step 1: Set the goal explicitly
- Step 2: Detect the domain
- Step 3: Derive scenarios from acceptance criteria + diff
- Step 4: Run the priority loop
- Step 5: Fix-and-retest
- Step 6: Capture the trajectory as a permanent test
- Step 7: Confirm the goal is met
- Anti-patterns
- Flow position
- References
Files
SKILL.mdcore11,226 bytesreferences/backend.mddoc11,688 bytesreferences/ui.mddoc9,128 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubstaleness-audit
When your agent uses it
Pre-commit audit. Invoke before every git commit. Diffs the staged change against the repo's "canaries" (README, decision log, roadmap, public API, doc comments, release notes, test discipline) and surfaces anything that's drifted out of sync. Updates the obvious drifts in place; flags judgement calls for the operator.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
2,520 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- How to invoke
- Inputs
- Procedure
- Output
- Invoke `/flagrare:write-docs` for documentation drift
- Anti-patterns (what this skill is not)
- After this skill: invoke `/flagrare:release-check`
- Why this exists
Files
SKILL.mdcore10,812 bytesSKILL.mdcore10,812 bytesSKILL.mdcore10,812 bytesSKILL.mdcore10,812 bytesSKILL.mdcore10,812 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubstandup-report
When your agent uses it
Generate a two-part standup report: Yesterday (everything code-related you shipped, reviewed, or addressed since your last working day, PRs merged, reviews left and answered, comments addressed, deploys that fired, tickets closed) and Today (carry-over threads plus priority-ordered queue items, framed as "likely working today"). Pulls from GitHub, local git, release automation, and any installed tracker/Slack MCPs. Output is a narrative paragraph, a journal-style recap, a Today section, and a slack-pasteable bullet list, written in human terms (the *thing* you fixed, not "PR
What it loads into context
Frontmatter
214 tokensAlways available to the agent
SKILL.md
7,981 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Setup (first run only)
- Resolve the time window
- Data collection
- Naming work in human terms
- Pin every event to a real date before you write
- Narrative synthesis
- Report format
- Edge cases
- Output
Files
SKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytesSKILL.mdcore32,930 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtdd-writer
When your agent uses it
Draft comprehensive Technical Design Documents. Analyzes codebase, fetches ticket/design/doc context via MCP. Every technical claim is verified against actual code. Unverified information is explicitly marked. Use when the user wants to write a TDD, create a technical design document, plan a large engineering project, or says 'write a TDD'.
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
4,855 tokensWhen the skill is activated
Reference documents
1,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- No Assumptions Policy
- Workflow
- Key Principles
- Anti-patterns
Files
../../../../docs/research/2026-06-11-claude-code-goal-anti-stall.mddoc8,314 bytesSKILL.mdcore21,425 bytesSKILL.mdcore21,425 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtesting-philosophy
When your agent uses it
Use when proposing, writing, or reviewing automated tests, defines what a good test is: behavior over implementation details, and the Testing Trophy with a hard floor on end-to-end coverage for user-facing features. Generalized to any language and any layer (frontend, backend, CLI, library), not just JS/React. REQUIRED BACKGROUND for skills that plan or review tests, atdd-plan, implementation-review, tdd-writer, wrap-up. Use when the user asks whether tests are good, what to test, why a test is brittle, or whether e2e is needed.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,775 tokensWhen the skill is activated
Reference documents
2,425 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- The one principle
- Pillar 1: Behavior over implementation details
- Pillar 2: The Testing Trophy, and the e2e floor
- How skills use this
- Anti-patterns
- Source
Files
../../../../docs/research/2026-06-11-kent-dodds-testing-philosophy.mddoc10,583 bytesSKILL.mdcore7,753 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubticket-creator
When your agent uses it
Create well-structured tickets as reviewable markdown files, then push to any tracker (Jira, Linear, Trello, Asana, Shortcut) via MCP or CLI after user review. Grounds each ticket in actual code by calling /flagrare:codebase-explore before drafting, and polishes the Context section via /flagrare:write-docs. Use when the user asks to create tickets, file bugs, write stories, create tasks, build a backlog, or convert specs/TDDs into implementation tickets.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
7,546 tokensWhen the skill is activated
Reference documents
1,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Keep tickets short
- Write for three readers
- When to Use
- Step 0: Detect the Tracker
- Step 0.25: Match the Team's Precedent (Backlogs)
- Step 0.5: Ground the Ticket in Code (Pre-Draft)
- Output Format
- Title Convention
- Issue Types
- Ticket Body Templates
- Polish the Context (Post-Draft): REQUIRED, not optional
- Sizing
- Acceptance Criteria Best Practices
- Workflow: Single Ticket
- Workflow: Spec/TDD to Backlog
- Presenting the result
- Workflow: Push to Tracker
- Anti-patterns
Files
../../../../docs/research/2026-06-11-claude-code-goal-anti-stall.mddoc8,314 bytesSKILL.mdcore31,904 bytesSKILL.mdcore31,904 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubtutor
When your agent uses it
Socratic tutor mode. Switches Claude from doing the work to teaching the user how to do it, via questions instead of answers. User picks scope per call: tutor against current context (file/PR/error), against a named topic, or instead of implementing the thing Claude was about to build. Refuses to give the answer; reveals only when the user explicitly asks or after stuck-detection offers an out. Closes only on explicit close phrase ('stop tutoring', 'end tutor', etc.), no model-side mastery gate. Only triggers on explicit intent: 'tutor me on X', 'tutor me through this', 'tutor mode', 'be my tutor', 'act as a tutor', 'Socratic me', 'use the Socratic method', 'use the tutor skill', '/flagrare:tutor', or 'I don't want the answer, I want to understand'. Does NOT auto-trigger on colloquial phrases like 'teach me', 'explain this', or 'walk me through', those usually mean the user just wants a quick answer.
What it loads into context
Frontmatter
223 tokensAlways available to the agent
SKILL.md
4,184 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 0: Learning-path log check (per-repo, opt-in)
- Step 1: Pick the scope
- Step 2: Pick the persona
- Step 3: Enter the chosen scope branch
- Step 4: Socratic engine
- Step 5: Stuck-offer (escape hatch at 3 stalls)
- Step 6: Scaffolding ladder (reveal mode only)
- Negative examples: what the tutor must never do
- Step 7: Close
- Cross-skill integration
- Re-entry and interruption
Files
SKILL.mdcore17,190 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubui-review
When your agent uses it
Full UI pass on one screen, dialog or flow: runs /flagrare:ux-audit, /flagrare:design-review and /flagrare:interaction-polish together, in that order, on the same browser session and the same screenshots, then ships ONE findings report (a single severity-ranked list, each finding tagged UX / Design / Interaction, overlaps merged) followed by the fixes it applied and the principle behind each. The first-time-user walk drives the real UI and gathers the evidence; the design lens diagnoses those screenshots (system coverage inventory, squint test, subtraction, ranked top 3); the interaction lens works on the interactions the walk found (press feedback, loading and transition states, frequency-gated motion, reduced motion). When a demo or before/after is part of the output it ships an MP4 recorded in real time with a visible cursor, never a GIF stitched from screenshots. Use when the user says 'UI review', 'review this screen', 'full pass on this page', 'audit and polish this', 'design and UX pass', 'make this screen good', 'run all three UI skills', or names one screen and asks for UX, design and feel in one go. Use a single source skill instead when only one lens is wanted.
What it loads into context
Frontmatter
268 tokensAlways available to the agent
SKILL.md
3,437 tokensWhen the skill is activated
Reference documents
1,469 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Rules carried from the source skills
- Workflow
- Anti-patterns
- Flow position
Files
SKILL.mdcore14,496 bytesSKILL.mdcore14,496 bytesSKILL.mdcore14,496 bytesSKILL.mdcore14,496 bytesSKILL.mdcore14,496 bytesSKILL.mdcore14,496 bytesSKILL.mdcore14,496 bytesSKILL.mdcore14,496 bytesreferences/demo-video.mddoc5,715 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubuninstall
When your agent uses it
Uninstall the flagrare plugin and remove the marketplace. Use when the user says 'uninstall flagrare', 'remove flagrare', 'disable flagrare skills', or 'remove flagrare-skills'.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
248 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
Scripts executed separately
../../../../uninstall.sh
Files
SKILL.mdcore1,009 bytesSKILL.mdcore1,009 bytesSKILL.mdcore1,009 bytes../../../../uninstall.shruns312 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubupdate
When your agent uses it
Pull the latest flagrare skills from GitHub. Use when the user says 'update skills', 'refresh skills', 'pull latest skills', 'update flagrare', or 'sync skills'.
What it loads into context
Frontmatter
46 tokensAlways available to the agent
SKILL.md
307 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Procedure
Files
SKILL.mdcore1,299 bytesSKILL.mdcore1,299 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubux-audit
When your agent uses it
Goal-locked UX audit. Drives a real browser through every reachable route (or a user-specified scope) and every visible affordance, screenshots each state, and ships a severity-ranked findings table (High/Medium/Low) with location, why-it's-painful, and recommended fix. Installs Chrome DevTools MCP automatically if missing. Pretends to be a first-time user, surfaces jargon, mystery glyphs, dead-ends, choice paralysis, color-only signals, jarring tone, broken empty states. Use when the user says 'UX audit', 'test all paths', 'click through everything', 'pretend to be a user', 'find painful flows', 'find UX issues', 'usability pass', 'walk through the app', or after a feature lands and before a release. Triggers even if 'audit' isn't in the request, any phrasing about exhaustively trying the app from a user's perspective qualifies.
What it loads into context
Frontmatter
199 tokensAlways available to the agent
SKILL.md
4,755 tokensWhen the skill is activated
Reference documents
3,806 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Why this exists
- Called by `/flagrare:ui-review`
- Step 1: Lock the goal explicitly
- Step 2: Enumerate routes from the source
- Step 3: Setup the browser
- Step 4: Walk each route, exhaustively
- Step 5: Log findings as you go (not at the end)
- Step 6: Compile the executive summary
- Step 7: Hand off
- Coverage discipline
- When to deviate
- Output contract
Files
SKILL.mdcore20,488 bytesSKILL.mdcore20,488 bytesSKILL.mdcore20,488 bytesSKILL.mdcore20,488 bytesSKILL.mdcore20,488 bytesSKILL.mdcore20,488 bytesSKILL.mdcore20,488 bytesreferences/finding-triggers.mddoc9,357 bytesreferences/findings-template.mddoc3,210 bytesreferences/severity-rubric.mddoc3,816 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubvisual-diff-branches
When your agent uses it
Use when the question is how pages render on one git ref versus another: checking a design-system, tokens, typography or styling PR for visual regressions on your feature's pages, producing before/after screenshots for a designer, answering 'did this branch change how X looks', or when a screenshot comparison is needed and no image library (ImageMagick, Pillow, sharp, pixelmatch) is installed. Triggers on 'compare main vs this branch', 'before and after screenshots', 'visual regression on this PR', 'what changed visually', 'side by side for design'.
What it loads into context
Frontmatter
128 tokensAlways available to the agent
SKILL.md
1,909 tokensWhen the skill is activated
Reference documents
663 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Step 1: Decide what "the branch" means
- Step 2: Write `shots.mjs`
- Step 3: Capture, one variant at a time
- Step 4: Measure, do not squint
- Step 5: Diff and compose
- Step 6: Report and clean up
- Common mistakes
Scripts executed separately
references/shots.example.mjsscripts/capture.mjsscripts/compare-measures.mjsscripts/compose.mjsscripts/diff.mjsscripts/lib.mjsscripts/measure.mjsscripts/wait-for-rebuild.sh
Files
SKILL.mdcore8,063 bytesreferences/config.mddoc2,545 bytesreferences/shots.example.mjsruns3,804 bytesscripts/capture.mjsruns2,325 bytesscripts/compare-measures.mjsruns1,577 bytesscripts/compose.mjsruns2,557 bytesscripts/diff.mjsruns3,198 bytesscripts/lib.mjsruns1,525 bytesscripts/measure.mjsruns2,514 bytesscripts/wait-for-rebuild.shruns1,172 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwork-prep
When your agent uses it
Orchestrates the full preparation workflow for a ticket. Calls /flagrare:intake (which gathers context from Jira/Notion/Figma, grounds the brief in the codebase via /flagrare:codebase-explore, then asks codebase-informed clarifying questions), then hands the codebase-grounded brief to /flagrare:atdd-plan for a TDD-first implementation plan. Use when the user shares a ticket key (e.g. SKU-123), says 'start work on', 'pick up ticket', 'plan this feature', 'work prep', or provides a Jira URL.
What it loads into context
Frontmatter
133 tokensAlways available to the agent
SKILL.md
2,000 tokensWhen the skill is activated
Reference documents
1,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Anti-patterns
- Critical: The handoff mechanism
- Flow position
Files
../../../../docs/research/2026-06-11-claude-code-goal-anti-stall.mddoc8,314 bytesSKILL.mdcore8,314 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrap-up
When your agent uses it
Post-implementation quality gate. Runs automated checks (tests, lint, types), invokes /flagrare:implementation-review for the seven-check parallel review, culls every code comment in the diff that is not a trap-preventer, then performs additional SOLID and Clean Code review on any findings not covered. Use when the user says 'wrap up', 'review changes', 'check my work', 'am I done', or after completing an implementation task.
What it loads into context
Frontmatter
100 tokensAlways available to the agent
SKILL.md
2,275 tokensWhen the skill is activated
Reference documents
1,869 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Workflow
- Anti-patterns
- Flow position
Files
../../../../docs/research/2026-06-11-claude-code-goal-anti-stall.mddoc8,314 bytesSKILL.mdcore9,307 bytesSKILL.mdcore9,307 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubwrite-docs
When your agent uses it
Write documentation that reads like a person wrote it for another person. The skill teaches the craft layer first, how to set context, how to calibrate tone, how to escape the curse of knowledge, when prose beats a bullet list, and only then the structural conventions (Diátaxis modes, README landing-page arc). Use whenever you're writing or restructuring a README, a docs tree, a CONTRIBUTING file, a guide, an architecture document, or any other documentation surface.
What it loads into context
Frontmatter
103 tokensAlways available to the agent
SKILL.md
6,227 tokensWhen the skill is activated
Reference documents
0 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to invoke
- The procedure
- Anti-patterns
- Cross-references
- Why this exists
Files
SKILL.mdcore28,487 bytes
No excerpt is shown for this license. Read the source on GitHub.
View the complete source on GitHubSkills included
- atdd-plan
- brag-doc
- bug-bash
- career
- codebase-explore
- daily-code-review
- debug-hunt
- design-review
- editorial-pass
- figma-matcher
- five-lens-review
- impact-scan
- impact-timeline
- implementation-review
- intake
- interaction-polish
- measure-impact
- open-pr
- opportunity-scan
- playbook
- pr-reviewer
- promotion
- release-check
- research-catalog
- security-audit
- smoke-test
- staleness-audit
- standup-report
- tdd-writer
- testing-philosophy
- ticket-creator
- tutor
- ui-review
- uninstall
- update
- ux-audit
- visual-diff-branches
- work-prep
- wrap-up
- write-docs
Repository facts
- License
- No license detected
- Created
- May 18, 2026
- Last pushed
- Nov 4, 2026
- Forks
- 2
- Open issues
- 0
- Project activity
- Active
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 4, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 145 notes
plugins/flagrare/hooks/post_skill_chain.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/hooks/pre_atdd_plan_gate.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/hooks/research_catalog_reminder.sh:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/evals/evals.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/evals/evals.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/measure-impact/evals/evals.json:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/brag-doc/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedplugins/flagrare/skills/bug-bash/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 4 dangerous shell commandsin 2 files: plugins/flagrare/skills/uninstall/SKILL.md:36 plugins/flagrare/skills/update/SKILL.md:22
- No hidden or obfuscated text
- No instruction overrides
- 24 executable scriptsin 13 files: plugins/flagrare/hooks/post_skill_chain.sh:1 plugins/flagrare/hooks/pre_atdd_plan_gate.sh:1 plugins/flagrare/hooks/research_catalog_reminder.sh:1 and 10 more
- 8 references to secretsin 2 files: plugins/flagrare/skills/write-docs/SKILL.md:78 plugins/flagrare/skills/tdd-writer/SKILL.md:291
- No requests to vote in Hot
Show all 437 signals by file
.claude-plugin/marketplace.json
docs/research/2026-06-11-claude-code-goal-anti-stall.md
- Network accessline 15
### [Keep Claude working toward a goal](https://code.claude.com/docs/en/goal) - Network accessline 15
### [Keep Claude working toward a goal](https://code.claude.com/docs/en/goal) - Network accessline 15
### [Keep Claude working toward a goal](https://code.claude.com/docs/en/goal) - Network accessline 15
### [Keep Claude working toward a goal](https://code.claude.com/docs/en/goal) - Network accessline 15
### [Keep Claude working toward a goal](https://code.claude.com/docs/en/goal) - Network accessline 15
### [Keep Claude working toward a goal](https://code.claude.com/docs/en/goal) - Network accessline 15
### [Keep Claude working toward a goal](https://code.claude.com/docs/en/goal) - Network accessline 33
### [Commands / Slash commands: Claude Code Docs](https://code.claude.com/docs/en/slash-commands) - Network accessline 33
### [Commands / Slash commands: Claude Code Docs](https://code.claude.com/docs/en/slash-commands) - Network accessline 33
### [Commands / Slash commands: Claude Code Docs](https://code.claude.com/docs/en/slash-commands) - Network accessline 33
### [Commands / Slash commands: Claude Code Docs](https://code.claude.com/docs/en/slash-commands) - Network accessline 33
### [Commands / Slash commands: Claude Code Docs](https://code.claude.com/docs/en/slash-commands) - Network accessline 33
### [Commands / Slash commands: Claude Code Docs](https://code.claude.com/docs/en/slash-commands) - Network accessline 33
### [Commands / Slash commands: Claude Code Docs](https://code.claude.com/docs/en/slash-commands)
docs/research/2026-06-11-kent-dodds-testing-philosophy.md
- Network accessline 15
### [Testing Implementation Details](https://kentcdodds.com/blog/testing-implementation-details) - Network accessline 28
### [The Testing Trophy and Testing Classifications](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications) - Network accessline 39
### [Write tests. Not too many. Mostly integration.](https://kentcdodds.com/blog/write-tests) (via on-site search summary) - **Authors / Org:** Kent C. Dodds (phrase originated in a tweet by Guillermo Rauch) - **Type:** engineering blog (se
docs/research/2026-07-03-editorial-pass-prior-art.md
- Network accessline 15
### [haowjy/creative-writing-skills](https://github.com/haowjy/creative-writing-skills) - Network accessline 27
### [anthropics/skills: doc-coauthoring](https://github.com/anthropics/skills/blob/main/skills/doc-coauthoring/SKILL.md) - Network accessline 33
### [blader/humanizer](https://github.com/blader/humanizer) and [Aboudjem/humanizer-skill](https://github.com/Aboudjem/humanizer-skill) - Network accessline 39
### [SNL-UCSB/paper-writing-skill](https://github.com/SNL-UCSB/paper-writing-skill) - Network accessline 45
### [obra/the-elements-of-style](https://github.com/obra/the-elements-of-style), [jamditis/claude-skills-journalism](https://github.com/jamditis/claude-skills-journalism), [anthropics skill-authoring best practices](https://platform.claude.
docs/research/2026-09-14-open-code-review-teardown.md
- Network accessline 3
**Research date:** 2026-09-14 **Source:** [alibaba/open-code-review](https://github.com/alibaba/open-code-review), Apache-2.0, read locally at `~/Dev/labs/open-code-review` - Network accessline 3
**Research date:** 2026-09-14 **Source:** [alibaba/open-code-review](https://github.com/alibaba/open-code-review), Apache-2.0, read locally at `~/Dev/labs/open-code-review` - Network accessline 4
**Source:** [alibaba/open-code-review](https://github.com/alibaba/open-code-review), Apache-2.0, read locally at `~/Dev/labs/open-code-review` - Network accessline 4
**Source:** [alibaba/open-code-review](https://github.com/alibaba/open-code-review), Apache-2.0, read locally at `~/Dev/labs/open-code-review`
plugins/flagrare/.claude-plugin/plugin.json
plugins/flagrare/hooks/measure_reminders.py
- Executable scriptline 1
#!/usr/bin/env python3
plugins/flagrare/hooks/post_skill_chain.sh
plugins/flagrare/hooks/pre_atdd_plan_gate.sh
plugins/flagrare/hooks/research_catalog_reminder.sh
plugins/flagrare/skills/bug-bash/evals/evals.json
- Network accessline 5
"id": 1, "name": "notion-source-with-writeback", "prompt": "Hey, can you bash the Workspace Invites feature for me? Test cases are in our Notion page: https://www.notion.so/myteam/Workspace-Invites-3646a78f120780b0a945c0a07a32e6 - Network accessline 5
"id": 1, "name": "notion-source-with-writeback", "prompt": "Hey, can you bash the Workspace Invites feature for me? Test cases are in our Notion page: https://www.notion.so/myteam/Workspace-Invites-3646a78f120780b0a945c0a07a32e6 - Network accessline 6
"name": "notion-source-with-writeback", "prompt": "Hey, can you bash the Workspace Invites feature for me? Test cases are in our Notion page: https://www.notion.so/myteam/Workspace-Invites-3646a78f120780b0a945c0a07a32e698. I'm logged - Network accessline 6
"name": "notion-source-with-writeback", "prompt": "Hey, can you bash the Workspace Invites feature for me? Test cases are in our Notion page: https://www.notion.so/myteam/Workspace-Invites-3646a78f120780b0a945c0a07a32e698. I'm logged - Network accessline 7
"prompt": "Hey, can you bash the Workspace Invites feature for me? Test cases are in our Notion page: https://www.notion.so/myteam/Workspace-Invites-3646a78f120780b0a945c0a07a32e698. I'm logged in to staging at app.example.com already. When - Network accessline 7
"prompt": "Hey, can you bash the Workspace Invites feature for me? Test cases are in our Notion page: https://www.notion.so/myteam/Workspace-Invites-3646a78f120780b0a945c0a07a32e698. I'm logged in to staging at app.example.com already. When
plugins/flagrare/skills/bug-bash/references/backend.md
- Network accessline 15
Use Postman when you'll hit the same endpoint multiple times across the bash, variables let you reuse auth and base URLs without retyping. Use curl for one-shot calls or when scripting a sequence. - Network accessline 15
Use Postman when you'll hit the same endpoint multiple times across the bash, variables let you reuse auth and base URLs without retyping. Use curl for one-shot calls or when scripting a sequence. - Network accessline 21
- **Build a data pool**: call the list endpoint for every venue or account the user can see, keep the eligible ids (a 403 also tells you which ones they can't). - **Run the negative matrix fast**: another tenant's id, past the window, blank - Network accessline 21
- **Build a data pool**: call the list endpoint for every venue or account the user can see, keep the eligible ids (a 403 also tells you which ones they can't). - **Run the negative matrix fast**: another tenant's id, past the window, blank - Network accessline 23
- **Race**: `await Promise.all(Array.from({length: 10}, () => fetch(...)))` with the same body, then count rows. One success and N-1 refusals is the pass; check whether a unique index or just a check-then-insert is holding the line. - Network accessline 23
- **Race**: `await Promise.all(Array.from({length: 10}, () => fetch(...)))` with the same body, then count rows. One success and N-1 refusals is the pass; check whether a unique index or just a check-then-insert is holding the line. - Network accessline 40
Status: 201 Headers: { Content-Type: application/json, X-Request-Id: abc123 } Body: { "id": "uuid-...", "link": "https://..." } - Network accessline 40
Status: 201 Headers: { Content-Type: application/json, X-Request-Id: abc123 } Body: { "id": "uuid-...", "link": "https://..." } - Network accessline 42
Body: { "id": "uuid-...", "link": "https://..." } - Network accessline 42
Body: { "id": "uuid-...", "link": "https://..." }
plugins/flagrare/skills/career/evals/fixtures/contributions.log.md
- Network accessline 3
- 2026-09-21 | https://example.com/thread/21 | answered a question about partner payouts | behavior: unblocking others - Network accessline 3
- 2026-09-21 | https://example.com/thread/21 | answered a question about partner payouts | behavior: unblocking others - Network accessline 4
- 2026-09-23 | https://example.com/thread/23 | answered a question about partner payouts | behavior: unblocking others - Network accessline 4
- 2026-09-23 | https://example.com/thread/23 | answered a question about partner payouts | behavior: unblocking others - Network accessline 5
- 2026-09-26 | https://example.com/thread/26 | answered a question about partner payouts | behavior: unblocking others - Network accessline 5
- 2026-09-26 | https://example.com/thread/26 | answered a question about partner payouts | behavior: unblocking others - Network accessline 6
- 2026-09-29 | https://example.com/thread/29 | answered a question about partner payouts | behavior: unblocking others - Network accessline 6
- 2026-09-29 | https://example.com/thread/29 | answered a question about partner payouts | behavior: unblocking others
plugins/flagrare/skills/career/evals/fixtures/flags.json
- Network accessline 3
"section": "calendar", "reason": "HR published the review calendar", "source": "https://example.com/hr/calendar", - Network accessline 3
"section": "calendar", "reason": "HR published the review calendar", "source": "https://example.com/hr/calendar", - Network accessline 4
"reason": "HR published the review calendar", "source": "https://example.com/hr/calendar", "raised_at": "2026-09-30" - Network accessline 4
"reason": "HR published the review calendar", "source": "https://example.com/hr/calendar", "raised_at": "2026-09-30" - Network accessline 5
"source": "https://example.com/hr/calendar", - Network accessline 5
"source": "https://example.com/hr/calendar",
plugins/flagrare/skills/career/evals/fixtures/initiatives.json
- Network accessline 4
"title": "Partners not getting order emails", "evidence": [ "https://example.com/incidents/41", - Network accessline 4
"title": "Partners not getting order emails", "evidence": [ "https://example.com/incidents/41", - Network accessline 5
"evidence": [ "https://example.com/incidents/41", "https://example.com/support/9" - Network accessline 5
"evidence": [ "https://example.com/incidents/41", "https://example.com/support/9" - Network accessline 6
"https://example.com/incidents/41", - Network accessline 6
"https://example.com/incidents/41", - Network accessline 7
"https://example.com/support/9" - Network accessline 7
"https://example.com/support/9"
plugins/flagrare/skills/career/evals/fixtures/promotion-map.json
- Network accessline 3
"current_level": { "value": "Software Engineer III", "source": "https://example.com/ladder", - Network accessline 3
"current_level": { "value": "Software Engineer III", "source": "https://example.com/ladder", - Network accessline 4
"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 4
"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 5
"source": "https://example.com/ladder", - Network accessline 5
"source": "https://example.com/ladder", - Network accessline 9
"target_level": { "value": "Senior Software Engineer", "source": "https://example.com/ladder", - Network accessline 9
"target_level": { "value": "Senior Software Engineer", "source": "https://example.com/ladder", - Network accessline 10
"value": "Senior Software Engineer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 10
"value": "Senior Software Engineer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 11
"source": "https://example.com/ladder", - Network accessline 11
"source": "https://example.com/ladder", - Network accessline 15
"cycle": { "value": "January 2027", "source": "https://example.com/ladder", - Network accessline 15
"cycle": { "value": "January 2027", "source": "https://example.com/ladder", - Network accessline 16
"value": "January 2027", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 16
"value": "January 2027", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 17
"source": "https://example.com/ladder", - Network accessline 17
"source": "https://example.com/ladder", - Network accessline 31
"artifact": { "value": "product gate document", "source": "https://example.com/ladder", - Network accessline 31
"artifact": { "value": "product gate document", "source": "https://example.com/ladder", - Network accessline 32
"value": "product gate document", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 32
"value": "product gate document", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 33
"source": "https://example.com/ladder", - Network accessline 33
"source": "https://example.com/ladder", - Network accessline 37
"usual_driver": { "value": "PM", "source": "https://example.com/ladder", - Network accessline 37
"usual_driver": { "value": "PM", "source": "https://example.com/ladder", - Network accessline 38
"value": "PM", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 38
"value": "PM", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 39
"source": "https://example.com/ladder", - Network accessline 39
"source": "https://example.com/ladder", - Network accessline 47
"packet_deadline": { "value": "2027-01-07", "source": "https://example.com/ladder", - Network accessline 47
"packet_deadline": { "value": "2027-01-07", "source": "https://example.com/ladder", - Network accessline 48
"value": "2027-01-07", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 48
"value": "2027-01-07", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 49
"source": "https://example.com/ladder", - Network accessline 49
"source": "https://example.com/ladder", - Network accessline 66
"current_text": { "value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", - Network accessline 66
"current_text": { "value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", - Network accessline 67
"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 67
"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 68
"source": "https://example.com/ladder", - Network accessline 68
"source": "https://example.com/ladder", - Network accessline 72
"target_text": { "value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", - Network accessline 72
"target_text": { "value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", - Network accessline 73
"value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 73
"value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 74
"source": "https://example.com/ladder", - Network accessline 74
"source": "https://example.com/ladder", - Network accessline 90
"role": { "value": "Engineering Manager", "source": "https://example.com/ladder", - Network accessline 90
"role": { "value": "Engineering Manager", "source": "https://example.com/ladder", - Network accessline 91
"value": "Engineering Manager", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 91
"value": "Engineering Manager", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 92
"source": "https://example.com/ladder", - Network accessline 92
"source": "https://example.com/ladder", - Network accessline 103
"role": { "value": "Director of Engineering", "source": "https://example.com/ladder", - Network accessline 103
"role": { "value": "Director of Engineering", "source": "https://example.com/ladder", - Network accessline 104
"value": "Director of Engineering", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 104
"value": "Director of Engineering", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 105
"source": "https://example.com/ladder", - Network accessline 105
"source": "https://example.com/ladder",
plugins/flagrare/skills/figma-matcher/SKILL.md
- Network accessline 52
3. **`get_design_context`** on SMALL nodes only — one atomic piece at a time (a header cell, a row cell, a button, a menu). Large frames silently degrade to sparse metadata with a note telling you to recurse into sublayers; budget for one c - Network accessline 52
3. **`get_design_context`** on SMALL nodes only — one atomic piece at a time (a header cell, a row cell, a button, a menu). Large frames silently degrade to sparse metadata with a note telling you to recurse into sublayers; budget for one c - Network accessline 54
5. **Optional, most exact: Figma REST API** — `GET https://api.figma.com/v1/files/:key/nodes?ids=:nodeId` with an `X-Figma-Token` PAT returns the raw node JSON: fills/strokes as r/g/b/a **floats 0-1 (multiply by 255)**, `cornerRadius`, auto - Network accessline 54
5. **Optional, most exact: Figma REST API** — `GET https://api.figma.com/v1/files/:key/nodes?ids=:nodeId` with an `X-Figma-Token` PAT returns the raw node JSON: fills/strokes as r/g/b/a **floats 0-1 (multiply by 255)**, `cornerRadius`, auto
plugins/flagrare/skills/impact-scan/SKILL.md
- Network accessline 274
"source": "github", "kind": "review", "action": "Point out the flyout always shows the last 7 days", "link": "https://...", "context": "Whose thing, what it is, where it stands", - Network accessline 274
"source": "github", "kind": "review", "action": "Point out the flyout always shows the last 7 days", "link": "https://...", "context": "Whose thing, what it is, where it stands", - Network accessline 275
"action": "Point out the flyout always shows the last 7 days", "link": "https://...", "context": "Whose thing, what it is, where it stands", "why": "Impact in 12 words or less", "behavior": "raising the quality bar", "rubric_rows": - Network accessline 275
"action": "Point out the flyout always shows the last 7 days", "link": "https://...", "context": "Whose thing, what it is, where it stands", "why": "Impact in 12 words or less", "behavior": "raising the quality bar", "rubric_rows": - Network accessline 276
"link": "https://...", "context": "Whose thing, what it is, where it stands", - Network accessline 276
"link": "https://...", "context": "Whose thing, what it is, where it stands",
plugins/flagrare/skills/impact-scan/evals/fixtures/initiatives.json
- Network accessline 1
[{ "id": "order-emails-missing", "title": "Partners not getting order emails", "evidence": ["https://example.com/incidents/41"], "seen_count": 1, - Network accessline 1
[{ "id": "order-emails-missing", "title": "Partners not getting order emails", "evidence": ["https://example.com/incidents/41"], "seen_count": 1,
plugins/flagrare/skills/impact-scan/evals/fixtures/own-work-items.json
- Network accessline 1
[ {"source": "github", "link": "https://github.com/acme/admin/pull/3209", "title": "[Spike] Place a test order from the venue page", "date": "2026-10-09", "keys": ["SKU-1020"], "links": ["https://app.notion.com/p/test-orders-design"]}, - Network accessline 1
[ {"source": "github", "link": "https://github.com/acme/admin/pull/3209", "title": "[Spike] Place a test order from the venue page", "date": "2026-10-09", "keys": ["SKU-1020"], "links": ["https://app.notion.com/p/test-orders-design"]}, - Network accessline 2
{"source": "github", "link": "https://github.com/acme/admin/pull/3209", "title": "[Spike] Place a test order from the venue page", "date": "2026-10-09", "keys": ["SKU-1020"], "links": ["https://app.notion.com/p/test-orders-design"]}, - Network accessline 2
{"source": "github", "link": "https://github.com/acme/admin/pull/3209", "title": "[Spike] Place a test order from the venue page", "date": "2026-10-09", "keys": ["SKU-1020"], "links": ["https://app.notion.com/p/test-orders-design"]}, - Network accessline 3
{"source": "github", "link": "https://github.com/acme/admin/pull/3243", "title": "[SKU-1034] Add the test order account config", "date": "2026-10-21", "keys": ["SKU-1034", "SKU-1033"], "links": ["https://app.notion.com/p/test-orders-design" - Network accessline 3
{"source": "github", "link": "https://github.com/acme/admin/pull/3243", "title": "[SKU-1034] Add the test order account config", "date": "2026-10-21", "keys": ["SKU-1034", "SKU-1033"], "links": ["https://app.notion.com/p/test-orders-design" - Network accessline 4
{"source": "github", "link": "https://github.com/acme/admin/pull/3272", "title": "[SKU-1039] Place and cancel the test order from the dialog", "date": "2026-10-26", "keys": ["SKU-1039", "SKU-1033"], "links": []}, - Network accessline 4
{"source": "github", "link": "https://github.com/acme/admin/pull/3272", "title": "[SKU-1039] Place and cancel the test order from the dialog", "date": "2026-10-26", "keys": ["SKU-1039", "SKU-1033"], "links": []}, - Network accessline 5
{"source": "notion", "link": "https://app.notion.com/p/test-orders-design", "title": "Mini design doc: admin test orders", "date": "2026-10-20", "keys": ["SKU-1033"], "links": []}, - Network accessline 5
{"source": "notion", "link": "https://app.notion.com/p/test-orders-design", "title": "Mini design doc: admin test orders", "date": "2026-10-20", "keys": ["SKU-1033"], "links": []}, - Network accessline 6
{"source": "granola", "link": "https://notes.granola.ai/d/retro-oct-21", "title": "Sprint retro: kudos for the test order work, and how the team should explore with AI", "date": "2026-10-21", "keys": [], "links": ["https://app.notion.com/p/ - Network accessline 6
{"source": "granola", "link": "https://notes.granola.ai/d/retro-oct-21", "title": "Sprint retro: kudos for the test order work, and how the team should explore with AI", "date": "2026-10-21", "keys": [], "links": ["https://app.notion.com/p/
plugins/flagrare/skills/impact-scan/evals/fixtures/promotion-map.json
- Network accessline 1
{ "target": { "current_level": {"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 1
{ "target": { "current_level": {"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 2
"target": { "current_level": {"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, "target_level": {"value": "Senior Software Engineer", "source": "https://exam - Network accessline 2
"target": { "current_level": {"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, "target_level": {"value": "Senior Software Engineer", "source": "https://exam - Network accessline 3
"current_level": {"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 3
"current_level": {"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 4
"target_level": {"value": "Senior Software Engineer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"} - Network accessline 4
"target_level": {"value": "Senior Software Engineer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"} - Network accessline 7
"rows": [ {"id": "scope.proactive-discovery", "area": "Scope & Impact", "status": "partial", "current_text": {"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09- - Network accessline 7
"rows": [ {"id": "scope.proactive-discovery", "area": "Scope & Impact", "status": "partial", "current_text": {"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09- - Network accessline 8
{"id": "scope.proactive-discovery", "area": "Scope & Impact", "status": "partial", "current_text": {"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": " - Network accessline 8
{"id": "scope.proactive-discovery", "area": "Scope & Impact", "status": "partial", "current_text": {"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": " - Network accessline 9
"current_text": {"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 9
"current_text": {"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 10
"target_text": {"value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 10
"target_text": {"value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 11
"evidence": []}, {"id": "craft.review-quality", "area": "Technical Craft", "status": "done", "current_text": {"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status - Network accessline 11
"evidence": []}, {"id": "craft.review-quality", "area": "Technical Craft", "status": "done", "current_text": {"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status - Network accessline 12
{"id": "craft.review-quality", "area": "Technical Craft", "status": "done", "current_text": {"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 12
{"id": "craft.review-quality", "area": "Technical Craft", "status": "done", "current_text": {"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 13
"current_text": {"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 13
"current_text": {"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 14
"target_text": {"value": "Sought-after reviewer for their stack", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 14
"target_text": {"value": "Sought-after reviewer for their stack", "source": "https://example.com/ladder", "checked_at": "2026-09-30", "status": "verified"}, - Network accessline 15
"evidence": ["- 2026-09-20 | https://example.com/pr/1 | caught a data-loss bug in review | behavior: raising the quality bar"]} - Network accessline 15
"evidence": ["- 2026-09-20 | https://example.com/pr/1 | caught a data-loss bug in review | behavior: raising the quality bar"]} - Network accessline 17
}, "people": [ {"name": "Sam Rivera", "role": {"value": "Engineering Manager", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "current manager", "seen_your_work": true, "evidence": - Network accessline 17
}, "people": [ {"name": "Sam Rivera", "role": {"value": "Engineering Manager", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "current manager", "seen_your_work": true, "evidence": - Network accessline 18
"people": [ {"name": "Sam Rivera", "role": {"value": "Engineering Manager", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "current manager", "seen_your_work": true, "evidence": [], " - Network accessline 18
"people": [ {"name": "Sam Rivera", "role": {"value": "Engineering Manager", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "current manager", "seen_your_work": true, "evidence": [], " - Network accessline 19
{"name": "Sam Rivera", "role": {"value": "Engineering Manager", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "current manager", "seen_your_work": true, "evidence": [], "confirmed_by_use - Network accessline 19
{"name": "Sam Rivera", "role": {"value": "Engineering Manager", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "current manager", "seen_your_work": true, "evidence": [], "confirmed_by_use - Network accessline 20
{"name": "Alex Chen", "role": {"value": "Director of Engineering", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "skip level, starts next month", "seen_your_work": false, "evidence": [], - Network accessline 20
{"name": "Alex Chen", "role": {"value": "Director of Engineering", "source": "https://example.com/org", "checked_at": "2026-09-30", "status": "verified"}, "relation": "skip level, starts next month", "seen_your_work": false, "evidence": [],
plugins/flagrare/skills/impact-timeline/references/playbook.md
- Network accessline 56
3. Extract numbers via the platform's API from the authenticated page (rendered embeds are unreliable). Mode specifically: - Trigger a report run in the UI, note report token + run token from the URL. - `fetch('/api/{ws}/reports/{repo - Network accessline 56
3. Extract numbers via the platform's API from the authenticated page (rendered embeds are unreliable). Mode specifically: - Trigger a report run in the UI, note report token + run token from the URL. - `fetch('/api/{ws}/reports/{repo - Network accessline 57
- Trigger a report run in the UI, note report token + run token from the URL. - `fetch('/api/{ws}/reports/{report}/runs/{run}')` until state=succeeded (often seconds even when the embed spins). - `fetch('/api/{ws}/reports/{report}/run - Network accessline 57
- Trigger a report run in the UI, note report token + run token from the URL. - `fetch('/api/{ws}/reports/{report}/runs/{run}')` until state=succeeded (often seconds even when the embed spins). - `fetch('/api/{ws}/reports/{report}/run - Network accessline 58
- `fetch('/api/{ws}/reports/{report}/runs/{run}')` until state=succeeded (often seconds even when the embed spins). - Network accessline 58
- `fetch('/api/{ws}/reports/{report}/runs/{run}')` until state=succeeded (often seconds even when the embed spins). - Network accessline 59
- `fetch('/api/{ws}/reports/{report}/runs/{run}/query_runs')` lists named queries; each query's rows at `.../query_runs/{qr}/results/content.json`. - Network accessline 59
- `fetch('/api/{ws}/reports/{report}/runs/{run}/query_runs')` lists named queries; each query's rows at `.../query_runs/{qr}/results/content.json`.
plugins/flagrare/skills/intake/SKILL.md
- Network accessline 49
Accept any of: - A bare ticket ID: `INT-42`, `ch12345`, `PROJ-99` - A full URL: `https://linear.app/…`, `https://company.atlassian.net/…` - Network accessline 49
Accept any of: - A bare ticket ID: `INT-42`, `ch12345`, `PROJ-99` - A full URL: `https://linear.app/…`, `https://company.atlassian.net/…` - Network accessline 50
- A bare ticket ID: `INT-42`, `ch12345`, `PROJ-99` - A full URL: `https://linear.app/…`, `https://company.atlassian.net/…` - A plain-text description pasted inline, treat as the ticket body directly, skip Steps 2-3 - Network accessline 50
- A bare ticket ID: `INT-42`, `ch12345`, `PROJ-99` - A full URL: `https://linear.app/…`, `https://company.atlassian.net/…` - A plain-text description pasted inline, treat as the ticket body directly, skip Steps 2-3 - Network accessline 51
- A full URL: `https://linear.app/…`, `https://company.atlassian.net/…` - Network accessline 51
- A full URL: `https://linear.app/…`, `https://company.atlassian.net/…`
plugins/flagrare/skills/measure-impact/evals/evals.json
- Network accessline 4
{ "id": 0, "prompt": "Before I build it: how will we know if the new 'save my usual order' shortcut for Acme Pizza works? Ticket https://tracker.example/T-5. My files are in ~/.claude/skills/flagrare/ (see the fixtures).", - Network accessline 4
{ "id": 0, "prompt": "Before I build it: how will we know if the new 'save my usual order' shortcut for Acme Pizza works? Ticket https://tracker.example/T-5. My files are in ~/.claude/skills/flagrare/ (see the fixtures).", - Network accessline 5
"id": 0, "prompt": "Before I build it: how will we know if the new 'save my usual order' shortcut for Acme Pizza works? Ticket https://tracker.example/T-5. My files are in ~/.claude/skills/flagrare/ (see the fixtures).", "expect - Network accessline 5
"id": 0, "prompt": "Before I build it: how will we know if the new 'save my usual order' shortcut for Acme Pizza works? Ticket https://tracker.example/T-5. My files are in ~/.claude/skills/flagrare/ (see the fixtures).", "expect - Network accessline 6
"prompt": "Before I build it: how will we know if the new 'save my usual order' shortcut for Acme Pizza works? Ticket https://tracker.example/T-5. My files are in ~/.claude/skills/flagrare/ (see the fixtures).", - Network accessline 6
"prompt": "Before I build it: how will we know if the new 'save my usual order' shortcut for Acme Pizza works? Ticket https://tracker.example/T-5. My files are in ~/.claude/skills/flagrare/ (see the fixtures).",
plugins/flagrare/skills/measure-impact/evals/fixtures/contributions.log.md
- Network accessline 3
- 2026-09-20 | https://tracker.example/T-1 | Shipped the reorder button for Acme Pizza | behavior: team-first - Network accessline 3
- 2026-09-20 | https://tracker.example/T-1 | Shipped the reorder button for Acme Pizza | behavior: team-first - Network accessline 4
- 2026-09-24 | https://chat.example/p7 | Found that a nightly job sent duplicate receipts to 3% of Acme Pizza's customers, and got it fixed | behavior: team-first - Network accessline 4
- 2026-09-24 | https://chat.example/p7 | Found that a nightly job sent duplicate receipts to 3% of Acme Pizza's customers, and got it fixed | behavior: team-first
plugins/flagrare/skills/measure-impact/evals/fixtures/measurements.json
- Network accessline 1
[ { "id": "acme-reorder", "work": { "title": "Reorder button for Acme Pizza", "link": "https://tracker.example/T-1", "kind": "ticket" }, - Network accessline 1
[ { "id": "acme-reorder", "work": { "title": "Reorder button for Acme Pizza", "link": "https://tracker.example/T-1", "kind": "ticket" }, - Network accessline 2
{ "id": "acme-reorder", "work": { "title": "Reorder button for Acme Pizza", "link": "https://tracker.example/T-1", "kind": "ticket" }, - Network accessline 2
{ "id": "acme-reorder", "work": { "title": "Reorder button for Acme Pizza", "link": "https://tracker.example/T-1", "kind": "ticket" },
plugins/flagrare/skills/opportunity-scan/evals/fixtures/initiatives-with-active.json
- Network accessline 4
"title": "Checkout tests fail at random", "evidence": [ "https://example.com/ci/3" - Network accessline 4
"title": "Checkout tests fail at random", "evidence": [ "https://example.com/ci/3" - Network accessline 5
"evidence": [ "https://example.com/ci/3" ], - Network accessline 5
"evidence": [ "https://example.com/ci/3" ], - Network accessline 6
"https://example.com/ci/3" - Network accessline 6
"https://example.com/ci/3" - Network accessline 22
"title": "Partners not getting order emails", "evidence": [ "https://example.com/incidents/41", - Network accessline 22
"title": "Partners not getting order emails", "evidence": [ "https://example.com/incidents/41", - Network accessline 23
"evidence": [ "https://example.com/incidents/41", "https://example.com/support/9" - Network accessline 23
"evidence": [ "https://example.com/incidents/41", "https://example.com/support/9" - Network accessline 24
"https://example.com/incidents/41", - Network accessline 24
"https://example.com/incidents/41", - Network accessline 25
"https://example.com/support/9" - Network accessline 25
"https://example.com/support/9"
plugins/flagrare/skills/opportunity-scan/evals/fixtures/initiatives.json
- Network accessline 4
"title": "Partners not getting order emails", "evidence": [ "https://example.com/incidents/41", - Network accessline 4
"title": "Partners not getting order emails", "evidence": [ "https://example.com/incidents/41", - Network accessline 5
"evidence": [ "https://example.com/incidents/41", "https://example.com/support/9" - Network accessline 5
"evidence": [ "https://example.com/incidents/41", "https://example.com/support/9" - Network accessline 6
"https://example.com/incidents/41", - Network accessline 6
"https://example.com/incidents/41", - Network accessline 7
"https://example.com/support/9" - Network accessline 7
"https://example.com/support/9"
plugins/flagrare/skills/opportunity-scan/evals/fixtures/promotion-map.json
- Network accessline 3
"current_level": { "value": "Software Engineer III", "source": "https://example.com/ladder", - Network accessline 3
"current_level": { "value": "Software Engineer III", "source": "https://example.com/ladder", - Network accessline 4
"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 4
"value": "Software Engineer III", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 5
"source": "https://example.com/ladder", - Network accessline 5
"source": "https://example.com/ladder", - Network accessline 9
"target_level": { "value": "Senior Software Engineer", "source": "https://example.com/ladder", - Network accessline 9
"target_level": { "value": "Senior Software Engineer", "source": "https://example.com/ladder", - Network accessline 10
"value": "Senior Software Engineer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 10
"value": "Senior Software Engineer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 11
"source": "https://example.com/ladder", - Network accessline 11
"source": "https://example.com/ladder", - Network accessline 15
"cycle": { "value": "January 2027", "source": "https://example.com/ladder", - Network accessline 15
"cycle": { "value": "January 2027", "source": "https://example.com/ladder", - Network accessline 16
"value": "January 2027", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 16
"value": "January 2027", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 17
"source": "https://example.com/ladder", - Network accessline 17
"source": "https://example.com/ladder", - Network accessline 32
"artifact": { "value": "product gate document", "source": "https://example.com/ladder", - Network accessline 32
"artifact": { "value": "product gate document", "source": "https://example.com/ladder", - Network accessline 33
"value": "product gate document", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 33
"value": "product gate document", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 34
"source": "https://example.com/ladder", - Network accessline 34
"source": "https://example.com/ladder", - Network accessline 38
"usual_driver": { "value": "PM", "source": "https://example.com/ladder", - Network accessline 38
"usual_driver": { "value": "PM", "source": "https://example.com/ladder", - Network accessline 39
"value": "PM", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 39
"value": "PM", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 40
"source": "https://example.com/ladder", - Network accessline 40
"source": "https://example.com/ladder", - Network accessline 48
"packet_deadline": { "value": "2027-01-07", "source": "https://example.com/ladder", - Network accessline 48
"packet_deadline": { "value": "2027-01-07", "source": "https://example.com/ladder", - Network accessline 49
"value": "2027-01-07", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 49
"value": "2027-01-07", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 50
"source": "https://example.com/ladder", - Network accessline 50
"source": "https://example.com/ladder", - Network accessline 61
"current_text": { "value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", - Network accessline 61
"current_text": { "value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", - Network accessline 62
"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 62
"value": "Given a problem, finds the right solution", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 63
"source": "https://example.com/ladder", - Network accessline 63
"source": "https://example.com/ladder", - Network accessline 67
"target_text": { "value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", - Network accessline 67
"target_text": { "value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", - Network accessline 68
"value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 68
"value": "Proactively discovers and solves problems the team is facing", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 69
"source": "https://example.com/ladder", - Network accessline 69
"source": "https://example.com/ladder", - Network accessline 79
"current_text": { "value": "Timely, constructive reviewer", "source": "https://example.com/ladder", - Network accessline 79
"current_text": { "value": "Timely, constructive reviewer", "source": "https://example.com/ladder", - Network accessline 80
"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 80
"value": "Timely, constructive reviewer", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 81
"source": "https://example.com/ladder", - Network accessline 81
"source": "https://example.com/ladder", - Network accessline 85
"target_text": { "value": "Sought-after reviewer for their stack", "source": "https://example.com/ladder", - Network accessline 85
"target_text": { "value": "Sought-after reviewer for their stack", "source": "https://example.com/ladder", - Network accessline 86
"value": "Sought-after reviewer for their stack", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 86
"value": "Sought-after reviewer for their stack", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 87
"source": "https://example.com/ladder", - Network accessline 87
"source": "https://example.com/ladder", - Network accessline 98
"role": { "value": "Engineering Manager", "source": "https://example.com/ladder", - Network accessline 98
"role": { "value": "Engineering Manager", "source": "https://example.com/ladder", - Network accessline 99
"value": "Engineering Manager", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 99
"value": "Engineering Manager", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 100
"source": "https://example.com/ladder", - Network accessline 100
"source": "https://example.com/ladder", - Network accessline 111
"role": { "value": "Director of Engineering", "source": "https://example.com/ladder", - Network accessline 111
"role": { "value": "Director of Engineering", "source": "https://example.com/ladder", - Network accessline 112
"value": "Director of Engineering", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 112
"value": "Director of Engineering", "source": "https://example.com/ladder", "checked_at": "2026-09-30", - Network accessline 113
"source": "https://example.com/ladder", - Network accessline 113
"source": "https://example.com/ladder", - Network accessline 145
"checked_at": "2026-09-30", "sources": [ "https://example.com/themes" - Network accessline 145
"checked_at": "2026-09-30", "sources": [ "https://example.com/themes" - Network accessline 146
"sources": [ "https://example.com/themes" ] - Network accessline 146
"sources": [ "https://example.com/themes" ] - Network accessline 147
"https://example.com/themes" - Network accessline 147
"https://example.com/themes" - Network accessline 154
"metric": { "value": "Merchant satisfaction score", "source": "https://example.com/themes", - Network accessline 154
"metric": { "value": "Merchant satisfaction score", "source": "https://example.com/themes", - Network accessline 155
"value": "Merchant satisfaction score", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 155
"value": "Merchant satisfaction score", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 156
"source": "https://example.com/themes", - Network accessline 156
"source": "https://example.com/themes", - Network accessline 160
"baseline": { "value": "32", "source": "https://example.com/themes", - Network accessline 160
"baseline": { "value": "32", "source": "https://example.com/themes", - Network accessline 161
"value": "32", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 161
"value": "32", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 162
"source": "https://example.com/themes", - Network accessline 162
"source": "https://example.com/themes", - Network accessline 171
"metric": { "value": "Share of orders where the venue gets no alert", "source": "https://example.com/themes", - Network accessline 171
"metric": { "value": "Share of orders where the venue gets no alert", "source": "https://example.com/themes", - Network accessline 172
"value": "Share of orders where the venue gets no alert", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 172
"value": "Share of orders where the venue gets no alert", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 173
"source": "https://example.com/themes", - Network accessline 173
"source": "https://example.com/themes", - Network accessline 177
"baseline": { "value": "12%", "source": "https://example.com/themes", - Network accessline 177
"baseline": { "value": "12%", "source": "https://example.com/themes", - Network accessline 178
"value": "12%", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 178
"value": "12%", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 179
"source": "https://example.com/themes", - Network accessline 179
"source": "https://example.com/themes", - Network accessline 188
"metric": { "value": "App conversion from search to booking", "source": "https://example.com/themes", - Network accessline 188
"metric": { "value": "App conversion from search to booking", "source": "https://example.com/themes", - Network accessline 189
"value": "App conversion from search to booking", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 189
"value": "App conversion from search to booking", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 190
"source": "https://example.com/themes", - Network accessline 190
"source": "https://example.com/themes", - Network accessline 194
"baseline": { "value": "not written down", "source": "https://example.com/themes", - Network accessline 194
"baseline": { "value": "not written down", "source": "https://example.com/themes", - Network accessline 195
"value": "not written down", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 195
"value": "not written down", "source": "https://example.com/themes", "checked_at": "2026-09-30", - Network accessline 196
"source": "https://example.com/themes", - Network accessline 196
"source": "https://example.com/themes",
plugins/flagrare/skills/pr-reviewer/SKILL.md
- Network accessline 243
- Cryptic: `The read-only Figma section already specs it (4051:28381: single full-width Close instead of Cancel/Save).` - Clear: `Design already has the read-only version of it: [node 4051-28381](https://figma.com/design/<key>?node-id=4051- - Network accessline 243
- Cryptic: `The read-only Figma section already specs it (4051:28381: single full-width Close instead of Cancel/Save).` - Clear: `Design already has the read-only version of it: [node 4051-28381](https://figma.com/design/<key>?node-id=4051- - Network accessline 244
- Clear: `Design already has the read-only version of it: [node 4051-28381](https://figma.com/design/<key>?node-id=4051-28381) shows the same modal with one full-width Close button in place of Cancel/Save.` - Network accessline 244
- Clear: `Design already has the read-only version of it: [node 4051-28381](https://figma.com/design/<key>?node-id=4051-28381) shows the same modal with one full-width Close button in place of Cancel/Save.`
plugins/flagrare/skills/release-check/SKILL.md
- Network accessline 292
11. **Confirm the artifact actually landed in the index.** Tooling can succeed-then-silently-skip. For PyPI: curl -s https://pypi.org/pypi/<package>/json | jq -r .info.version - Network accessline 292
11. **Confirm the artifact actually landed in the index.** Tooling can succeed-then-silently-skip. For PyPI: curl -s https://pypi.org/pypi/<package>/json | jq -r .info.version - Network accessline 293
can succeed-then-silently-skip. For PyPI: curl -s https://pypi.org/pypi/<package>/json | jq -r .info.version For crates.io: - Network accessline 293
can succeed-then-silently-skip. For PyPI: curl -s https://pypi.org/pypi/<package>/json | jq -r .info.version For crates.io: - Network accessline 294
curl -s https://pypi.org/pypi/<package>/json | jq -r .info.version - Network accessline 294
curl -s https://pypi.org/pypi/<package>/json | jq -r .info.version - Network accessline 413
- `/flagrare:staleness-audit` runs *before* the commit. This check runs *after* the commit lands, since release decisions depend on the version manifest + change-entry state post-commit. - Valve's Dota 2 patch notes: <https://www.dota2.com/ - Network accessline 413
- `/flagrare:staleness-audit` runs *before* the commit. This check runs *after* the commit lands, since release decisions depend on the version manifest + change-entry state post-commit. - Valve's Dota 2 patch notes: <https://www.dota2.com/ - Network accessline 414
- Valve's Dota 2 patch notes: <https://www.dota2.com/news/updates>, the canonical reference for the changelog style this skill enforces. - Network accessline 414
- Valve's Dota 2 patch notes: <https://www.dota2.com/news/updates>, the canonical reference for the changelog style this skill enforces.
plugins/flagrare/skills/research-catalog/SKILL.md
- Network accessline 140
- **Padding for credibility.** Citing ten sources to make the answer look researched when only three actually drove the conclusions. Cite the three. - **Citing only the convenient sources.** If the research surfaced a contradicting view (e. - Network accessline 140
- **Padding for credibility.** Citing ten sources to make the answer look researched when only three actually drove the conclusions. Cite the three. - **Citing only the convenient sources.** If the research surfaced a contradicting view (e. - Network accessline 141
- **Citing only the convenient sources.** If the research surfaced a contradicting view (e.g., persona prompting *hurts* factual accuracy on knowledge tasks), include it. Honest research has dissent. - **Bare-URL citations.** `[Anthropic pr - Network accessline 141
- **Citing only the convenient sources.** If the research surfaced a contradicting view (e.g., persona prompting *hurts* factual accuracy on knowledge tasks), include it. Honest research has dissent. - **Bare-URL citations.** `[Anthropic pr - Network accessline 142
- **Bare-URL citations.** `[Anthropic prompt engineering](https://platform.claude.com/…)`, not just the URL. Without a title the link is invisible to anyone scanning. - Network accessline 142
- **Bare-URL citations.** `[Anthropic prompt engineering](https://platform.claude.com/…)`, not just the URL. Without a title the link is invisible to anyone scanning.
plugins/flagrare/skills/tdd-writer/SKILL.md
plugins/flagrare/skills/testing-philosophy/SKILL.md
- Network accessline 89
Kent C. Dodds: [Testing Implementation Details](https://kentcdodds.com/blog/testing-implementation-details), [The Testing Trophy and Testing Classifications](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications), [Writ - Network accessline 89
Kent C. Dodds: [Testing Implementation Details](https://kentcdodds.com/blog/testing-implementation-details), [The Testing Trophy and Testing Classifications](https://kentcdodds.com/blog/the-testing-trophy-and-testing-classifications), [Writ
plugins/flagrare/skills/ui-review/references/demo-video.md
plugins/flagrare/skills/uninstall/SKILL.md
- Network accessline 34
> To reinstall later: > ```bash > bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh) - Network accessline 34
> To reinstall later: > ```bash > bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh) - Network accessline 35
> ```bash > bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh) > ``` - Network accessline 35
> ```bash > bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh) > ``` - Dangerous shell operationline 36
> bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh) - Dangerous shell operationline 36
> bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh) - Network accessline 36
> bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh) - Network accessline 36
> bash <(curl -sL https://raw.githubusercontent.com/Flagrare/flagrare-skills/main/install.sh)
plugins/flagrare/skills/update/SKILL.md
- Dangerous shell operationline 22
bash <(curl -sL https://raw.githubusercontent.com/Flagrare/agent-skills/main/update.sh) - Dangerous shell operationline 22
bash <(curl -sL https://raw.githubusercontent.com/Flagrare/agent-skills/main/update.sh) - Network accessline 22
bash <(curl -sL https://raw.githubusercontent.com/Flagrare/agent-skills/main/update.sh) - Network accessline 22
bash <(curl -sL https://raw.githubusercontent.com/Flagrare/agent-skills/main/update.sh)
plugins/flagrare/skills/visual-diff-branches/references/config.md
plugins/flagrare/skills/visual-diff-branches/references/shots.example.mjs
- Executable scriptline 1
Executable file - Executable scriptline 1
Executable file - Network accessline 17
export default { baseUrl: 'http://localhost:4545', - Network accessline 17
export default { baseUrl: 'http://localhost:4545', - Network accessline 18
baseUrl: 'http://localhost:4545', - Network accessline 18
baseUrl: 'http://localhost:4545',
plugins/flagrare/skills/visual-diff-branches/scripts/capture.mjs
plugins/flagrare/skills/visual-diff-branches/scripts/compare-measures.mjs
plugins/flagrare/skills/visual-diff-branches/scripts/compose.mjs
plugins/flagrare/skills/visual-diff-branches/scripts/diff.mjs
plugins/flagrare/skills/visual-diff-branches/scripts/lib.mjs
plugins/flagrare/skills/visual-diff-branches/scripts/measure.mjs
plugins/flagrare/skills/visual-diff-branches/scripts/wait-for-rebuild.sh
plugins/flagrare/skills/write-docs/SKILL.md
- Network accessline 14
- **[Steven Pinker, *The Sense of Style*](https://www.psychologicalscience.org/observer/the-curse-of-knowledge-pinker-describes-a-key-cause-of-bad-writing)** for *the curse of knowledge* and *classic style*. - Network accessline 14
- **[Steven Pinker, *The Sense of Style*](https://www.psychologicalscience.org/observer/the-curse-of-knowledge-pinker-describes-a-key-cause-of-bad-writing)** for *the curse of knowledge* and *classic style*. - Network accessline 15
- **[Chip & Dan Heath, *Made to Stick*](https://heathbrothers.com/made-to-stick-introduction/)** for *tappers and listeners* (Newton 1990) and concrete-over-abstract diction. - Network accessline 15
- **[Chip & Dan Heath, *Made to Stick*](https://heathbrothers.com/made-to-stick-introduction/)** for *tappers and listeners* (Newton 1990) and concrete-over-abstract diction. - Network accessline 16
- **[Mailchimp Content Style Guide](https://styleguide.mailchimp.com/voice-and-tone/)** for *voice is consistent, tone shifts*. - Network accessline 16
- **[Mailchimp Content Style Guide](https://styleguide.mailchimp.com/voice-and-tone/)** for *voice is consistent, tone shifts*. - Network accessline 17
- **[Diátaxis](https://diataxis.fr/)** + the celebrated landing pages (React, Stripe, Anthropic, SpacetimeDB, Tokio) for *structural shape*. - Network accessline 17
- **[Diátaxis](https://diataxis.fr/)** + the celebrated landing pages (React, Stripe, Anthropic, SpacetimeDB, Tokio) for *structural shape*. - Network accessline 43
There are four. They are not interchangeable, and most documentation problems are mode-confusion problems, a tutorial that's really a feature tour, a reference page that lectures, a how-to guide that opens with a paragraph of theory. The fo - Network accessline 43
There are four. They are not interchangeable, and most documentation problems are mode-confusion problems, a tutorial that's really a feature tour, a reference page that lectures, a how-to guide that opens with a paragraph of theory. The fo - Access to secretsline 78
[Credential-related source omitted] - Access to secretsline 78
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Access to secretsline 86
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted] - Access to secretsline 88
[Credential-related source omitted]
uninstall.sh
- Executable scriptline 1
#!/usr/bin/env bash
How the signals fit together
Facts from a static read of the files at the pinned commit. They describe what the code does, not why.
Some files could not be read; the facts below still hold.
Combined signals: 1 fact
- Passes content downloaded from raw.githubusercontent.com to an interpreterupdate/SKILL.md:22High confidence
Signal confidence: 158 facts
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-claude-code-goal-anti-stall.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-kent-dodds-testing-philosophy.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-kent-dodds-testing-philosophy.md:28Low confidence
- Network access in prose of documentationdocs/research/2026-06-11-kent-dodds-testing-philosophy.md:39Low confidence
- Network access in prose of documentationdocs/research/2026-07-03-editorial-pass-prior-art.md:15Low confidence
- Network access in prose of documentationdocs/research/2026-07-03-editorial-pass-prior-art.md:27Low confidence
- Network access in prose of documentationdocs/research/2026-07-03-editorial-pass-prior-art.md:33Low confidence
- Network access in prose of documentationdocs/research/2026-07-03-editorial-pass-prior-art.md:39Low confidence
- Network access in prose of documentationdocs/research/2026-07-03-editorial-pass-prior-art.md:45Low confidence
- Network access in prose of documentationdocs/research/2026-09-14-open-code-review-teardown.md:3Low confidence
- Network access in prose of documentationdocs/research/2026-09-14-open-code-review-teardown.md:3Low confidence
- Network access in prose of documentationdocs/research/2026-09-14-open-code-review-teardown.md:4Low confidence
- Network access in prose of documentationdocs/research/2026-09-14-open-code-review-teardown.md:4Low confidence
- Executable script in code of a file that runsplugins/flagrare/hooks/measure_reminders.py:1High confidence
- Executable script in code of a file that runsplugins/flagrare/hooks/post_skill_chain.sh:1High confidence
- Executable script in code of a file that runsplugins/flagrare/hooks/post_skill_chain.sh:1High confidence
- Executable script in code of a file that runsplugins/flagrare/hooks/pre_atdd_plan_gate.sh:1High confidence
- Executable script in code of a file that runsplugins/flagrare/hooks/pre_atdd_plan_gate.sh:1High confidence
- Executable script in code of a file that runsplugins/flagrare/hooks/research_catalog_reminder.sh:1High confidence
- Executable script in code of a file that runsplugins/flagrare/hooks/research_catalog_reminder.sh:1High confidence
- Network access in prose of documentationplugins/flagrare/skills/bug-bash/references/backend.md:15Low confidence
- Network access in prose of documentationbug-bash/references/backend.md:15Low confidence
- Network access in prose of documentationplugins/flagrare/skills/bug-bash/references/backend.md:21Low confidence
- Network access in prose of documentationbug-bash/references/backend.md:21Low confidence
- Network access in prose of documentationplugins/flagrare/skills/bug-bash/references/backend.md:23Low confidence
- Network access in prose of documentationbug-bash/references/backend.md:23Low confidence
- Network access in code of documentationplugins/flagrare/skills/bug-bash/references/backend.md:40Low confidence
- Network access in code of documentationbug-bash/references/backend.md:40Low confidence
- Network access in code of documentationplugins/flagrare/skills/bug-bash/references/backend.md:42Low confidence
- Network access in code of documentationbug-bash/references/backend.md:42Low confidence
- Network access in prose of a testplugins/flagrare/skills/career/evals/fixtures/contributions.log.md:3Low confidence
- Network access in prose of a testcareer/evals/fixtures/contributions.log.md:3Low confidence
- Network access in prose of a testplugins/flagrare/skills/career/evals/fixtures/contributions.log.md:4Low confidence
- Network access in prose of a testcareer/evals/fixtures/contributions.log.md:4Low confidence
- Network access in prose of a testplugins/flagrare/skills/career/evals/fixtures/contributions.log.md:5Low confidence
- Network access in prose of a testcareer/evals/fixtures/contributions.log.md:5Low confidence
- Network access in prose of a testplugins/flagrare/skills/career/evals/fixtures/contributions.log.md:6Low confidence
and 108 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Compatible | Standard SKILL.md plugins/flagrare/skills/atdd-plan/SKILL.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md plugins/flagrare/skills/atdd-plan/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md plugins/flagrare/skills/atdd-plan/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md plugins/flagrare/skills/atdd-plan/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md plugins/flagrare/skills/atdd-plan/SKILL.md | .opencode/skills/<skill-name>/ |
- Native The repository ships a manifest, folder or frontmatter field for this agent.
- Compatible A standard SKILL.md that this agent can read.
- Unknown No evidence either way.
Derived automatically from paths, manifests and frontmatter. Not tested on each agent.