#648 by GitHub stars
microsoft/waza
CLI / Framework for Agent Skills - create, test, measure and improve skill quality and effectiveness
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
.copilot/skills/squad-commands/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
.squad/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
.squad-templates/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
.squad-templates/skills/squad-conventions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
.squad/skills/squad-conventions/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
.squad/templates/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/dev/testdata/high/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/dev/testdata/minimal/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/dev/testdata/no-frontmatter/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/dev/testdata/valid/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/testdata/run/eval-skill-search/.github/skills/test-skill-a/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/testdata/run/eval-skill-search/.github/skills/test-skill-b/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Local scripts → After Local scripts
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Local scripts
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/tokens/testdata/check/all-pass/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/tokens/testdata/check/legacy-json-only/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/tokens/testdata/check/no-config/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/tokens/testdata/check/some-exceed/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/tokens/testdata/count/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
cmd/waza/tokens/testdata/profile/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
examples/code-explainer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
examples/evidence-judge/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
internal/testdata/compatibility/v1/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
skills/code-explainer/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
skills/waza/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
skills/waza-interactive/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Instructions only → After Instructions only
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Instructions only
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
waza-runner/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
6e8c54d64ea1 → f5789f75fa00
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → 6e8c54d64ea1
No earlier version was observed for comparison.
Verified commit f5789f75fa00924411734d07fd4012ba80e2154c
git clone --filter=blob:none --no-checkout https://github.com/microsoft/waza.git .hotskills/microsoft-waza && git -C .hotskills/microsoft-waza checkout --detach f5789f75fa00924411734d07fd4012ba80e2154c
# Copy each selected skill directory from .hotskills/microsoft-waza into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/microsoft/waza.git .hotskills/microsoft-waza && git -C .hotskills/microsoft-waza checkout --detach f5789f75fa00924411734d07fd4012ba80e2154c
# Copy each selected skill directory from .hotskills/microsoft-waza into .github/skills/<skill-name>/Heat
4.2- Star growth, last 7 daysAhead of 66% of tracked repositories
- Star growth, last 24 hoursAhead of 5% of tracked repositories
- Rank movement, last 7 daysAhead of 27% of tracked repositories
- Commits, last 30 daysAhead of 93% of tracked repositories
- Accounts asking about it through MCP, last 7 daysNot available
- Hot votes this weekAhead of 0% of tracked repositories
Heat never changes the order by stars, and sponsorship never touches it. How heat works
Stars over time
Individual skills in this repository
- squad-commands
.copilot/skills/squad-commands - {skill-name}
.squad - {skill-name}
.squad-templates - squad-conventions
.squad-templates/skills/squad-conventions - squad-conventions
.squad/skills/squad-conventions - {skill-name}
.squad/templates - pdf-processor
cmd/waza/dev/testdata/high - my-tool
cmd/waza/dev/testdata/minimal - no-frontmatter
cmd/waza/dev/testdata/no-frontmatter - pdf-processor
cmd/waza/dev/testdata/valid - test-skill-a
cmd/waza/testdata/run/eval-skill-search/.github/skills/test-skill-a - test-skill-b
cmd/waza/testdata/run/eval-skill-search/.github/skills/test-skill-b - all-pass
cmd/waza/tokens/testdata/check/all-pass - legacy-json-only
cmd/waza/tokens/testdata/check/legacy-json-only - no-config
cmd/waza/tokens/testdata/check/no-config - some-exceed
cmd/waza/tokens/testdata/check/some-exceed - count
cmd/waza/tokens/testdata/count - profile-test-skill
cmd/waza/tokens/testdata/profile - code-explainer
examples/code-explainer - evidence-judge
examples/evidence-judge - compatibility-skill
internal/testdata/compatibility/v1 - code-explainer
skills/code-explainer - waza
skills/waza - waza-interactive
skills/waza-interactive - waza-runner
waza-runner
How it works
squad-commands
When your agent uses it
Categorized catalog of common Squad operations. Coordinator reads this file and presents it as an interactive menu when the user asks for available commands or help.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
2,641 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
- Menu Presentation Rules
- Install & Upgrade
- Team Management
- Issues & PRs
- Plugins & Skills
- Model & Cost
- Sessions & State
Files
SKILL.mdcore10,727 bytes
Read SKILL.md
## Menu Presentation Rules
When the user triggers this skill ("squad commands", "help", "what can squad do", etc.):
1. **Category-level menu first.** Present category names as an `ask_user` choice list:
```
📋 Squad Commands — pick a category:
1. Install & Upgrade
2. Team Management
3. Issues & PRs
4. Plugins & Skills
5. Model & Cost
6. Sessions & State
```View the complete source on GitHub{skill-name}
When your agent uses it
{what this skill teaches agents}
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
145 tokensWhen the skill is activated
Reference documents
53,403 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Patterns
- Examples
- Anti-Patterns
Files
agents/basher/charter.mddoc3,476 bytesagents/basher/history.mddoc6,970 bytesagents/danny/charter.mddoc3,240 bytesagents/danny/history.mddoc287 bytesagents/edie/history.mddoc1,178 bytesagents/fact-checker/charter.mddoc3,597 bytesagents/fact-checker/history.mddoc96 bytesagents/kobayashi/history.mddoc3,518 bytesagents/linus/charter.mddoc3,923 bytesagents/linus/history.mddoc13,847 bytesagents/livingston/charter.mddoc3,226 bytesagents/livingston/history.mddoc8,403 bytesagents/rai/charter.mddoc4,222 bytesagents/rai/history.mddoc87 bytesagents/ralph/charter.mddoc1,563 bytesagents/rusty/charter.mddoc3,415 bytesagents/rusty/history.mddoc12,693 bytesagents/saul/charter.mddoc3,319 bytesagents/saul/history.mddoc3,593 bytesagents/scribe/charter.mddoc2,470 bytesagents/scribe/history.mddoc1,054 bytesagents/tess/charter.mddoc5,139 bytesagents/turk/charter.mddoc3,104 bytesagents/turk/history.mddoc4,426 bytesagents/virgil/charter.mddoc3,041 bytesagents/virgil/history.mddoc287 bytesagents/yen/charter.mddoc2,914 bytesagents/yen/history.mddoc289 bytescasting-history.jsonasset70 bytescasting-policy.jsonasset823 bytescasting-registry.jsonasset146 bytescasting-transactions.mddoc12,321 bytescasting/history.jsonasset1,155 bytescasting/legacy-v0.10.0/history.jsonasset593 bytescasting/legacy-v0.10.0/policy.jsonasset718 bytescasting/legacy-v0.10.0/registry.jsonasset1,389 bytescasting/policy.jsonasset718 bytescasting/registry-history.commit.jsonasset282 bytescasting/registry.jsonasset3,701 bytesceremonies.mddoc1,705 bytescharter.mddoc2,058 bytesconfig.jsonasset513 bytesconstraint-tracking.mddoc1,192 bytescopilot-instructions.mddoc1,818 bytesdecisions.mddoc25,958 bytesdecisions/inbox/copilot-directive-20260421.mddoc234 bytesdecisions/inbox/linus-agent-tool-injection.mddoc1,735 bytesdecisions/inbox/linus-custom-agent-support.mddoc1,232 bytesdecisions/inbox/linus-mock-includes-resources.mddoc1,688 bytesdecisions/inbox/linus-pr-conflicts.mddoc453 bytesdecisions/inbox/linus-pr96-feedback.mddoc369 bytesdecisions/inbox/livingston-custom-agent-docs.mddoc1,933 bytesdecisions/inbox/saul-doc-audit-2025-07-15.mddoc862 bytesgovernance.mddoc4,151 byteshistory.mddoc255 bytesidentity/now.mddoc173 bytesidentity/wisdom.mddoc397 byteslog/2026-02-18-baseline-implementation.mddoc629 byteslog/2026-02-18-ralph-board-scan.mddoc966 byteslog/2026-02-19-docs-overhaul.mddoc548 byteslog/2026-02-19-pr260-bpe-review.mddoc1,261 byteslog/2026-02-19-ralph-scan.mddoc298 byteslog/2026-02-19-trajectory-epic-planning.mddoc1,468 byteslog/2026-02-20-model-policy-overhaul.mddoc839 byteslog/2026-02-21-pr303-merge.mddoc802 byteslog/2026-02-22-openai-evals-analysis.mddoc304 byteslog/2026-02-26-performance-audit.mddoc1,688 byteslog/2026-03-05T00-26-rusty-token-diff-design.mddoc1,785 byteslog/2026-03-05T00-36-full-pipeline-activation.mddoc3,629 byteslog/2026-03-05T00-36-issue-assignment-pipeline.mddoc1,771 bytesmcp-config.mddoc2,501 bytesmemory/audit.jsonlasset0 bytesmemory/config.jsonasset321 bytesmemory/index.jsonasset3 bytesmodel-policy.mddoc4,975 bytesmulti-agent-format.mddoc887 bytesorchestration-log.mddoc1,198 bytesorchestration-log/.gitkeepasset0 bytesorchestration-log/2026-03-05T00-37-pipeline-wave-1.mddoc1,748 bytesorchestration-log/2026-03-05T00-37-pipeline-wave-2.mddoc1,642 bytesorchestration-log/2026-03-05T00-37-pipeline-wave-3.mddoc1,634 bytesorchestration-log/2026-03-05T00-37-pipeline-wave-4.mddoc2,130 bytesplugin-marketplace.mddoc2,437 bytesrai/policy.mddoc1,874 bytesralph-instructions.mddoc2,775 bytesraw-agent-output.mddoc1,336 bytesroster.mddoc2,075 bytesrouting.mddoc10,915 bytesrun-output.mddoc1,500 bytesscribe-charter.mddoc5,249 bytesskill.mdcore587 bytesskills/.gitkeepasset0 bytesteam.mddoc4,714 bytes
Read SKILL.md
## Context
{When and why this skill applies}
## Patterns
{Specific patterns, conventions, or approaches}
## Examples
{Code examples or references}
## Anti-Patterns
{What to avoid}View the complete source on GitHub{skill-name}
When your agent uses it
{what this skill teaches agents}
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
145 tokensWhen the skill is activated
Reference documents
6,678 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Patterns
- Examples
- Anti-Patterns
Files
casting-history.jsonasset70 bytescasting-policy.jsonasset756 bytescasting-registry.jsonasset19 bytesceremonies.mddoc978 bytescharter.mddoc2,053 bytesconstraint-tracking.mddoc1,192 bytescopilot-instructions.mddoc1,818 byteshistory.mddoc255 bytesidentity/now.mddoc209 bytesidentity/wisdom.mddoc384 bytesmcp-config.mddoc2,501 bytesmulti-agent-format.mddoc887 bytesorchestration-log.mddoc1,104 bytesplugin-marketplace.mddoc2,437 bytesraw-agent-output.mddoc1,336 bytesroster.mddoc2,075 bytesrouting.mddoc3,517 bytesrun-output.mddoc1,500 bytesscribe-charter.mddoc5,102 bytesskill.mdcore587 bytesworkflows/squad-ci.ymlasset421 bytesworkflows/squad-docs.ymlasset1,029 bytesworkflows/squad-heartbeat.ymlasset12,543 bytesworkflows/squad-insider-release.ymlasset2,297 bytesworkflows/squad-issue-assign.ymlasset6,424 bytesworkflows/squad-label-enforce.ymlasset6,851 bytesworkflows/squad-main-guard.ymlasset3,183 bytesworkflows/squad-preview.ymlasset1,757 bytesworkflows/squad-promote.ymlasset4,343 bytesworkflows/squad-release.ymlasset2,637 bytesworkflows/squad-triage.ymlasset11,259 bytesworkflows/sync-squad-labels.ymlasset6,776 bytes
Read SKILL.md
## Context
{When and why this skill applies}
## Patterns
{Specific patterns, conventions, or approaches}
## Examples
{Code examples or references}
## Anti-Patterns
{What to avoid}View the complete source on GitHubsquad-conventions
When your agent uses it
Core conventions and patterns used in the Squad codebase
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
824 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
- Context
- Patterns
- Examples
- Anti-Patterns
Files
SKILL.mdcore3,440 bytesSKILL.mdcore3,440 bytes
Read SKILL.md
## Context
These conventions apply to all work on the Squad CLI tool (`create-squad`). Squad is a zero-dependency Node.js package that adds AI agent teams to any project. Understanding these patterns is essential before modifying any Squad source code.
## Patterns
### Zero Dependencies
Squad has zero runtime dependencies. Everything uses Node.js built-ins (`fs`, `path`, `os`, `child_process`). Do not add packages to `dependencies` in `package.json`. This is a hard constraint, not a preference.
### Node.js Built-in Test Runner
Tests use `node:test` and `node:assert/strict` — no test frameworks. Run with `npm test`. Test files live in `test/`. The test command is `node --test test/`.
### Error Handling — `fatal()` Pattern
All user-facing errors use the `fatal(msg)` function which prints a red `✗` prefix and exits with code 1. Never throw unhandled exceptions or print raw stack traces. The global `uncaughtException` handler calls `fatal()` as a safety net.
View the complete source on GitHubsquad-conventions
When your agent uses it
Core conventions and patterns used in the Squad codebase
What it loads into context
Frontmatter
39 tokensAlways available to the agent
SKILL.md
824 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
- Context
- Patterns
- Examples
- Anti-Patterns
Files
SKILL.mdcore3,440 bytesSKILL.mdcore3,440 bytes
Read SKILL.md
## Context
These conventions apply to all work on the Squad CLI tool (`create-squad`). Squad is a zero-dependency Node.js package that adds AI agent teams to any project. Understanding these patterns is essential before modifying any Squad source code.
## Patterns
### Zero Dependencies
Squad has zero runtime dependencies. Everything uses Node.js built-ins (`fs`, `path`, `os`, `child_process`). Do not add packages to `dependencies` in `package.json`. This is a hard constraint, not a preference.
### Node.js Built-in Test Runner
Tests use `node:test` and `node:assert/strict` — no test frameworks. Run with `npm test`. Test files live in `test/`. The test command is `node --test test/`.
### Error Handling — `fatal()` Pattern
All user-facing errors use the `fatal(msg)` function which prints a red `✗` prefix and exits with code 1. Never throw unhandled exceptions or print raw stack traces. The global `uncaughtException` handler calls `fatal()` as a safety net.
View the complete source on GitHub{skill-name}
When your agent uses it
{what this skill teaches agents}
What it loads into context
Frontmatter
101 tokensAlways available to the agent
SKILL.md
145 tokensWhen the skill is activated
Reference documents
47,077 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Context
- Patterns
- Examples
- Anti-Patterns
Scripts executed separately
package.jsonralph-triage.jsscripts/notes/fetch.ps1scripts/notes/write-note.ps1
Files
README.mddoc7,041 bytesRai-charter.mddoc3,248 bytesafter-agent-reference.mddoc6,366 bytescasting-history.jsonasset70 bytescasting-policy.jsonasset823 bytescasting-reference.mddoc9,012 bytescasting-registry.jsonasset146 bytescasting/Futurama.jsonasset108 bytesceremonies.mddoc1,854 bytesceremony-reference.mddoc3,162 bytescharter.mddoc2,053 bytesclient-compatibility-reference.mddoc3,758 bytesconstraint-tracking.mddoc1,192 bytescooperative-rate-limiting.mddoc7,222 bytescopilot-agent.mddoc3,939 bytescopilot-instructions.mddoc3,584 bytesfact-checker-charter.mddoc2,781 bytesfact-checker-policy.mddoc7,092 byteshistory.mddoc255 bytesidentity/now.mddoc209 bytesidentity/wisdom.mddoc384 bytesissue-lifecycle.mddoc12,183 byteskeda-scaler.mddoc5,732 bytesloop.mddoc1,378 bytesmachine-capabilities.mddoc2,415 bytesmcp-config.mddoc2,357 bytesmodel-selection-reference.mddoc7,240 bytesmulti-agent-format.mddoc887 bytesnotes-protocol.mddoc5,513 bytesorchestration-log.mddoc1,104 bytespackage.jsonruns25 bytesplugin-marketplace.mddoc2,437 bytesprd-intake.mddoc3,311 bytesrai-policy.mddoc5,305 bytesralph-charter.mddoc2,236 bytesralph-circuit-breaker.mddoc10,439 bytesralph-instructions.mddoc2,775 bytesralph-reference.mddoc7,628 bytesralph-triage.jsruns16,967 bytesraw-agent-output.mddoc1,336 bytesroster.mddoc2,389 bytesrouting.mddoc1,789 bytesrun-output.mddoc1,500 bytesscribe-charter.mddoc2,026 bytesscripts/notes/fetch.ps1runs3,977 bytesscripts/notes/write-note.ps1runs5,449 bytessession-init-reference.mddoc7,194 bytesskill.mdcore587 bytesspawn-reference.mddoc9,558 bytessquad.agent.md.templateasset85,752 bytesworkflow-wiring-appendix-a-code-reviewer.mddoc6,535 bytesworkflow-wiring-appendix-b-documenter.mddoc6,335 bytesworkflow-wiring-guide.mddoc15,385 bytesworktree-reference.mddoc7,553 bytes
Read SKILL.md
## Context
{When and why this skill applies}
## Patterns
{Specific patterns, conventions, or approaches}
## Examples
{Code examples or references}
## Anti-Patterns
{What to avoid}View the complete source on GitHubpdf-processor
When your agent uses it
**WORKFLOW SKILL** - Process PDF files including text extraction, rotation, and merging. USE FOR: "extract PDF text", "rotate PDF", "merge PDFs", "split PDF pages", "convert PDF to text". DO NOT USE FOR: creating PDFs from scratch (use document-creator), editing PDF forms (use form-filler). INVOKES: pdf-tools MCP for extraction, file-system for I/O. FOR SINGLE OPERATIONS: Use pdf-tools MCP directly for simple extractions.
What it loads into context
Frontmatter
115 tokensAlways available to the agent
SKILL.md
264 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
- Instructions
- MCP Tools Used
- Prerequisites
Files
SKILL.mdcore1,110 bytes
Read SKILL.md
# PDF Processor
**WORKFLOW SKILL** - Handles complex PDF manipulation workflows.
## Instructions
1. Parse the user's request to determine the PDF operation
2. Use appropriate tools for the operation
3. Return results with status
## MCP Tools Used
| Step | Tool | Command | Purpose |
| ---- | ----------- | ------- | --------------------- |View the complete source on GitHubmy-tool
When your agent uses it
What it loads into context
Frontmatter
4 tokensAlways available to the agent
SKILL.md
15 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
Files
SKILL.mdcore49 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
29 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
- Instructions
Files
SKILL.mdcore125 bytes
Read SKILL.md
# No Frontmatter Skill
This SKILL.md has no YAML frontmatter at all. It's just plain markdown.
## Instructions
Do things.View the complete source on GitHubpdf-processor
When your agent uses it
Process PDF files including text extraction, rotation, and merging. USE FOR: "extract PDF text", "rotate PDF", "merge PDFs", "split PDF pages", "convert PDF to text". DO NOT USE FOR: creating PDFs from scratch (use document-creator), editing PDF forms (use form-filler).
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
154 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
- Instructions
- Examples
Files
SKILL.mdcore693 bytes
Read SKILL.md
# PDF Processor
Handles common PDF manipulation tasks including extraction, rotation, and merging.
## Instructions
1. Parse the user's request to determine the PDF operation
2. Use appropriate tools for the operation
3. Return results with status
## Examples
**User**: Extract text from my PDF
**Response**: I'll use the pdf-tools to extract text from your document.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
7 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
Files
SKILL.mdcore37 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
7 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
Files
SKILL.mdcore37 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
424 tokensWhen the skill is activated
Reference documents
18 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Behavior Guidelines
Files
.token-limits.jsonasset49 bytesREADME.mddoc27 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesreferences/one.mddoc35 bytesreferences/two.mddoc40 bytes
Read SKILL.md
```skill
---
name: test-skill
description: |
**TEST SKILL** - A sample skill for testing waza token counting.
USE FOR: testing token count command, verifying markdown scanning.
DO NOT USE FOR: actual agent operations.
---
# Test Skill
A demonstration skill used for testing the `waza tokens` command suite.
## Skill Activation Triggers
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
20 tokensWhen the skill is activated
Reference documents
11 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
.token-limits.jsonasset50 bytesREADME.mddoc50 bytesSKILL.mdcore96 bytes
Read SKILL.md
# Legacy Test Skill
A minimal skill for testing legacy .token-limits.json deprecation warning.View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
3 tokensWhen the skill is activated
Reference documents
4 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
Files
README.mddoc9 bytesSKILL.mdcore8 bytes
When your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
424 tokensWhen the skill is activated
Reference documents
18 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Behavior Guidelines
Files
.token-limits.jsonasset47 bytesREADME.mddoc27 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesreferences/one.mddoc35 bytesreferences/two.mddoc40 bytes
Read SKILL.md
```skill
---
name: test-skill
description: |
**TEST SKILL** - A sample skill for testing waza token counting.
USE FOR: testing token count command, verifying markdown scanning.
DO NOT USE FOR: actual agent operations.
---
# Test Skill
A demonstration skill used for testing the `waza tokens` command suite.
## Skill Activation Triggers
View the complete source on GitHubWhen your agent uses it
What it loads into context
Frontmatter
0 tokensAlways available to the agent
SKILL.md
424 tokensWhen the skill is activated
Reference documents
18 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Behavior Guidelines
Scripts executed separately
scripts/sample.py
Files
README.mddoc27 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesSKILL.mdcore1,608 bytesreferences/one.mddoc35 bytesreferences/two.mddoc40 bytesscripts/sample.pyruns164 bytes
Read SKILL.md
```skill
---
name: test-skill
description: |
**TEST SKILL** - A sample skill for testing waza token counting.
USE FOR: testing token count command, verifying markdown scanning.
DO NOT USE FOR: actual agent operations.
---
# Test Skill
A demonstration skill used for testing the `waza tokens` command suite.
## Skill Activation Triggers
View the complete source on GitHubprofile-test-skill
When your agent uses it
**PROFILE TEST** - A skill for testing the profile command. USE FOR: testing profile analysis, verifying structural metrics. DO NOT USE FOR: production use.
What it loads into context
Frontmatter
45 tokensAlways available to the agent
SKILL.md
301 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
- Activation Triggers
- Workflow
- Code Examples
- Configuration
- Guidelines
Files
SKILL.mdcore1,227 bytesSKILL.mdcore1,227 bytes
Read SKILL.md
# Profile Test Skill
A test skill used for verifying the `waza tokens profile` command.
## Activation Triggers
**Use this skill when:**
- Running profile analysis tests
- Verifying section counting
- Checking code block detection
## Workflow
1. **Parse the file** - Read SKILL.md and extract frontmatterView the complete source on GitHubcode-explainer
When your agent uses it
**UTILITY SKILL** - Explain code snippets, functions, and algorithms in plain language. USE FOR: explain code, what does this code do, break down this function, help me understand this, walk through this algorithm, clarify this logic, explain this snippet, describe what happens here. DO NOT USE FOR: writing new code (use code generation), fixing bugs (use debugging), refactoring (use refactoring skills), code review with action items. INVOKES: file reading tools to access code, language detection for tailored explanations. FOR SINGLE OPERATIONS: If the user just needs to see file contents, use file reading tools directly.
What it loads into context
Frontmatter
147 tokensAlways available to the agent
SKILL.md
1,146 tokensWhen the skill is activated
Reference documents
923 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Skill Activation Triggers
- Quick Reference
- Explanation Guidelines
- Examples
- Error Cases
- Integration Notes
Scripts executed separately
fixtures/factorial.pyfixtures/fetch_user.jsfixtures/squares.pygraders/explanation_quality.py
Files
README.mddoc3,770 bytesSKILL.mdcore4,659 bytesSKILL.mdcore4,659 byteseval.yamlasset1,756 bytesfixtures/factorial.pyruns82 bytesfixtures/fetch_user.jsruns313 bytesfixtures/squares.pyruns49 bytesfixtures/user_orders.sqlasset147 bytesgraders/explanation_quality.pyruns5,673 bytestasks/explain-js-async.yamlasset951 bytestasks/explain-list-comprehension.yamlasset1,010 bytestasks/explain-python-recursion.yamlasset1,031 bytestasks/explain-sql-join.yamlasset925 bytestrigger_tests.yamlasset2,143 bytes
Read SKILL.md
# Code Explainer
A skill that explains code snippets in clear, educational language. Helps developers understand unfamiliar code, algorithms, and programming patterns.
## Skill Activation Triggers
**Use this skill immediately when the user asks to:**
- "Explain this code"
- "What does this function do?"
- "Break down this algorithm"
- "Help me understand this snippet"
- "Walk me through this code"
- "What's happening in this file?"
View the complete source on GitHubevidence-judge
When your agent uses it
Read a supplied report and summarize its recorded status and numeric items.
What it loads into context
Frontmatter
21 tokensAlways available to the agent
SKILL.md
54 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
Files
SKILL.mdcore268 byteseval.yamlasset790 bytesfixtures/report.jsonasset32 bytestasks/report.yamlasset155 bytes
Read SKILL.md
Read the requested JSON file before answering. Report its status, item count,
and sum, using only the observed values. Do not modify the input file.View the complete source on GitHubcompatibility-skill
When your agent uses it
Read fixture status and report whether it is ready.
What it loads into context
Frontmatter
18 tokensAlways available to the agent
SKILL.md
34 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
Files
SKILL.mdcore174 bytesdashboard-legacy.jsonasset760 byteseval-1.0.yamlasset279 byteseval-1.4.yamlasset343 bytesgraders.yamlasset1,326 bytesresults-1.0.jsonasset937 bytesresults-1.4.jsonasset1,434 bytessnapshot-1.0.jsonasset899 bytestask.yamlasset338 byteswaza.lockasset262 bytes
Read SKILL.md
Read the fixture and report its ready state. Do not change configuration.View the complete source on GitHubcode-explainer
When your agent uses it
Explains code snippets in plain English, breaking down what the code does step by step. Perfect for learning, code reviews, or documentation.
What it loads into context
Frontmatter
37 tokensAlways available to the agent
SKILL.md
639 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
- Instructions
- Output Format
- Examples
- Behavior Guidelines
Files
SKILL.mdcore2,451 bytesSKILL.mdcore2,451 bytesSKILL.mdcore2,451 bytes
Read SKILL.md
# Code Explainer Skill
You are a code explanation expert. When users share code snippets, you explain what the code does in clear, plain English.
## Instructions
1. **Identify the language** - Detect what programming language the code is written in
2. **Break it down** - Explain the code step by step
3. **Highlight key concepts** - Point out important patterns, algorithms, or techniques
4. **Suggest improvements** - If appropriate, mention potential optimizations or best practices
## Output Format
Structure your explanation as:View the complete source on GitHubwaza
When your agent uses it
**WORKFLOW SKILL** - Evaluate AI agent skills using structured benchmarks with YAML specs, fixture isolation, and pluggable validators. USE FOR: run waza, waza help, run eval, run benchmark, evaluate skill, test agent, generate eval suite, init eval, compare results, score agent, agent evaluation, skill testing, cross-model comparison. DO NOT USE FOR: improving skill frontmatter (use waza dev), creating new skills from scratch (use skill-creator), token counting or budget checks (use waza tokens). INVOKES: Copilot SDK executor, mock engine, code/regex validators. FOR SINGLE OPERATIONS: use waza run directly for a single benchmark.
What it loads into context
Frontmatter
149 tokensAlways available to the agent
SKILL.md
1,804 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
- Help
- Commands
- Evaluation Spec Format
- Engines
- Validators
- Configuration
- Scoring Quick Reference
Files
SKILL.mdcore8,387 bytesSKILL.mdcore8,387 bytesSKILL.mdcore8,387 bytesSKILL.mdcore8,387 bytesSKILL.mdcore8,387 bytesSKILL.mdcore8,387 bytes
Read SKILL.md
# Waza
> "The way of technique — measure, refine, master."
A Go CLI tool for evaluating AI agent skills through structured benchmarks. Define test cases in YAML, run them against agent engines, and validate results with pluggable scoring validators.
## Help
When user says "waza help" or asks how to use waza:
```
╔══════════════════════════════════════════════════════════════════╗
║ WAZA - CLI Tool for Evaluating Agent Skills ║
╠══════════════════════════════════════════════════════════════════╣View the complete source on GitHubwaza-interactive
When your agent uses it
Interactive workflow partner for creating, testing, and improving AI agent skills with waza. USE FOR: run my evals, check my skill, compare models, create eval suite, debug failing tests, is my skill ready, ship readiness, interpret results, improve score. DO NOT USE FOR: general coding, non-skill work, writing skill content (use skill-authoring), improving frontmatter only (use sensei).
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
1,316 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
- Available MCP Tools
- Scenario 1: Create a New Eval
- Scenario 2: Run and Interpret Results
- Scenario 3: Compare Models
- Scenario 4: Debug a Failing Skill
- Scenario 5: Ship Readiness Check
- Conversation Style
Files
SKILL.mdcore5,358 bytestests/eval.yamlasset2,300 bytes
Read SKILL.md
# Waza Interactive
You are a workflow partner that orchestrates waza evaluations conversationally. Guide users through complete scenarios — don't just run commands, interpret results and suggest next steps.
## Available MCP Tools
Call these tools to execute waza operations:
| Tool | Purpose |
|------|---------|
| `waza_eval_list` | List available eval suites |
| `waza_eval_get` | Get eval spec details |
| `waza_eval_validate` | Validate eval YAML syntax |
| `waza_eval_run` | Execute an eval benchmark |View the complete source on GitHubwaza-runner
When your agent uses it
Run evaluations on Agent Skills to measure their effectiveness. USE FOR: "run skill evals", "evaluate my skill", "test skill quality", "check skill triggers", "skill compliance check", "measure skill performance", "run evals on [skill-name]", "grade skill execution". DO NOT USE FOR: writing skills (use skill-authoring), improving frontmatter (use sensei), or general testing unrelated to skills.
What it loads into context
Frontmatter
122 tokensAlways available to the agent
SKILL.md
626 tokensWhen the skill is activated
Reference documents
848 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- When to Use
- Commands
- Workflow
- Metrics Measured
- Grader Types
- Example Usage
- References
Files
SKILL.mdcore2,457 bytesSKILL.mdcore2,457 bytesreferences/EVAL-SPEC.mddoc3,171 bytes
Read SKILL.md
# Skill Eval Runner
> Evaluate Agent Skills like you evaluate AI Agents
This skill runs evaluations on other skills to measure their effectiveness using the same patterns that power AI agent evaluations.
## When to Use
- Running quality evaluations on a skill
- Testing if a skill triggers on correct prompts
- Measuring skill behavior quality
- Generating eval reports for CI/CD
## CommandsView the complete source on GitHubSkills included
- squad-commands
- {skill-name}
- {skill-name}
- squad-conventions
- squad-conventions
- {skill-name}
- pdf-processor
- my-tool
- pdf-processor
- profile-test-skill
- code-explainer
- evidence-judge
- compatibility-skill
- code-explainer
- waza
- waza-interactive
- waza-runner
Repository facts
- License
- MIT
- Created
- Feb 27, 2026
- Last pushed
- Nov 5, 2026
- Forks
- 98
- Open issues
- 53
- Project activity
- Active
Rank over the last 12 weeks
Now #648 · best #483 · down 97 in 30 days
- #636 from Oct 30 to Oct 31
- #639 on Nov 1
- #642 on Nov 2
- #646 on Nov 3
- #649 on Nov 4
- #648 since Nov 5
70 earlier periods
- #491 on Aug 2
- #497 on Aug 7
- #490 on Aug 9
- #512 on Aug 10
- #509 on Aug 11
- #507 on Aug 12
- #510 on Aug 13
- #511 on Aug 14
- #483 on Aug 15
- #486 on Aug 16
- #491 on Aug 17
- #505 on Aug 18
- #498 on Aug 19
- #500 on Aug 20
- #499 on Aug 21
- #483 on Aug 22
- #505 from Aug 23 to Aug 24
- #511 on Aug 25
- #505 on Aug 26
- #517 on Aug 28
- #501 on Aug 29
- #493 on Aug 30
- #518 on Sep 1
- #523 on Sep 3
- #506 on Sep 4
- #501 on Sep 5
- #515 on Sep 6
- #516 on Sep 7
- #535 on Sep 8
- #522 on Sep 9
- #529 on Sep 10
- #519 on Sep 12
- #517 on Sep 13
- #537 on Sep 14
- #537 on Sep 16
- #535 on Sep 17
- #537 on Sep 18
- #520 on Sep 19
- #536 on Sep 21
- #545 on Sep 22
- #539 on Sep 23
- #524 on Sep 25
- #528 on Sep 26
- #550 on Sep 27
- #552 on Sep 28
- #571 on Sep 29
- #554 on Sep 30
- #540 from Oct 1 to Oct 2
- #526 on Oct 3
- #527 on Oct 4
- #536 on Oct 5
- #547 on Oct 6
- #551 on Oct 7
- #571 on Oct 8
- #567 on Oct 9
- #552 on Oct 10
- #553 on Oct 11
- #569 on Oct 13
- #574 on Oct 14
- #570 on Oct 15
- #574 on Oct 16
- #565 on Oct 17
- #589 on Oct 20
- #595 on Oct 21
- #582 on Oct 22
- #577 on Oct 23
- #569 on Oct 24
- #633 on Oct 25
- #629 on Oct 28
- #633 on Oct 29
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 5, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 21 notes
.squad-templates/skills/squad-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.squad/skills/squad-conventions/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/check/all-pass/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/check/all-pass/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/check/all-pass/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/check/some-exceed/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/check/some-exceed/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/check/some-exceed/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/count/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/count/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/count/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcmd/waza/tokens/testdata/profile/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedexamples/code-explainer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/code-explainer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/code-explainer/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/waza/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/waza/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/waza/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/waza/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/waza/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- 5 dangerous shell commandsin 3 files: .squad-templates/workflows/squad-main-guard.yml:72 .squad-templates/workflows/squad-promote.yml:48 code-explainer/README.md:22
- 47 network referencesin 14 files: templates/ralph-triage.js:414 code-explainer/SKILL.md:106 templates/keda-scaler.md:7 and 11 more
- No hidden or obfuscated text
- 1 instruction override signalin 1 file: templates/model-selection-reference.md:50
- 11 executable scriptsin 11 files: templates/package.json:1 templates/ralph-triage.js:1 templates/scripts/notes/fetch.ps1:1 and 8 more
- 13 references to secretsin 4 files: .squad-templates/mcp-config.md:24 .squad/mcp-config.md:24 templates/mcp-config.md:22 and 1 more
- No requests to vote in Hot
Show all 77 signals by file
.squad-templates/mcp-config.md
- Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Network accessline 85
- **GitHub MCP requires a separate token** from the `gh` CLI auth. Generate at https://github.com/settings/tokens - Network accessline 86
- **Trello requires API key + token** from https://trello.com/power-ups/admin - Network accessline 88
- **Aspire uses the dashboard URL** — typically `http://localhost:18888` during local dev
.squad-templates/workflows/squad-main-guard.yml
.squad-templates/workflows/squad-promote.yml
- Dangerous shell operationline 48
git rm -rf --cached --ignore-unmatch \
.squad/agents/basher/history.md
- Network accessline 35
- **Tailwind v4 colors:** `getComputedStyle` returns `oklch()` not `rgb()` — assert lightness < 0.3 for dark theme - **react-query retries:** Default 3 retries with backoff; error state tests need ~15s timeout - **page.request vs page.evalu - Network accessline 36
- **react-query retries:** Default 3 retries with backoff; error state tests need ~15s timeout - **page.request vs page.evaluate:** `page.request.get()` bypasses route interception; use `page.evaluate(() => fetch(...))` instead - **Hash rou - Network accessline 37
- **page.request vs page.evaluate:** `page.request.get()` bypasses route interception; use `page.evaluate(() => fetch(...))` instead
.squad/log/2026-02-21-pr303-merge.md
- Network accessline 3
**Date:** 2026-02-21 **Requested by:** Shayne Boyer **PR:** [#303](https://github.com/microsoft/waza/pull/303) — Trajectory redesign - Network accessline 4
**Requested by:** Shayne Boyer **PR:** [#303](https://github.com/microsoft/waza/pull/303) — Trajectory redesign **Merged by:** @copilot (admin squash-merge) - Network accessline 5
**PR:** [#303](https://github.com/microsoft/waza/pull/303) — Trajectory redesign
.squad/mcp-config.md
- Access to secretsline 24
[Credential-related source omitted] - Access to secretsline 25
[Credential-related source omitted] - Access to secretsline 41
[Credential-related source omitted] - Access to secretsline 59
[Credential-related source omitted] - Network accessline 85
- **GitHub MCP requires a separate token** from the `gh` CLI auth. Generate at https://github.com/settings/tokens - Network accessline 86
- **Trello requires API key + token** from https://trello.com/power-ups/admin - Network accessline 88
- **Aspire uses the dashboard URL** — typically `http://localhost:18888` during local dev
.squad/templates/cooperative-rate-limiting.md
- Network accessline 216
See [keda-copilot-scaler](https://github.com/tamirdresher/keda-copilot-scaler) for a complete implementation. - Network accessline 227
- [Circuit Breaker Template](ralph-circuit-breaker.md) — Foundation patterns - [Squad on AKS](https://github.com/tamirdresher/squad-on-aks) — Production K8s deployment - Network accessline 228
- [Squad on AKS](https://github.com/tamirdresher/squad-on-aks) — Production K8s deployment - Network accessline 229
- [KEDA Copilot Scaler](https://github.com/tamirdresher/keda-copilot-scaler) — Custom KEDA external scaler
.squad/templates/keda-scaler.md
- Network accessline 7
When running Squad on Kubernetes, agent pods sit idle when no work exists. [KEDA](https://keda.sh) (Kubernetes Event-Driven Autoscaler) solves this for queue-based workloads, but GitHub Issues isn't a native KEDA trigger. - Network accessline 34
kubectl apply -k https://github.com/tamirdresher/keda-copilot-scaler/deploy/kustomize - Network accessline 151
- **Repository:** [tamirdresher/keda-copilot-scaler](https://github.com/tamirdresher/keda-copilot-scaler) - Network accessline 161
- [KEDA External Scalers](https://keda.sh/docs/latest/concepts/external-scalers/) — KEDA documentation - Network accessline 162
- [Squad on AKS](https://github.com/tamirdresher/squad-on-aks) — Full Kubernetes deployment example
.squad/templates/machine-capabilities.md
- Network accessline 75
A DaemonSet can run capability discovery on each node and maintain labels automatically. See the [squad-on-aks](https://github.com/tamirdresher/squad-on-aks) project for a complete Kubernetes deployment example.
.squad/templates/mcp-config.md
- Access to secretsline 22
[Credential-related source omitted] - Access to secretsline 23
[Credential-related source omitted] - Access to secretsline 39
[Credential-related source omitted] - Access to secretsline 57
[Credential-related source omitted] - Network accessline 83
- **GitHub MCP requires a separate token** from the `gh` CLI auth. Generate at https://github.com/settings/tokens - Network accessline 84
- **Trello requires API key + token** from https://trello.com/power-ups/admin - Network accessline 86
- **Aspire uses the dashboard URL** — typically `http://localhost:18888` during local dev
.squad/templates/model-selection-reference.md
- Instruction override signalline 50
If a spawn fails because the selected model is unavailable (plan restriction, org policy, rate limit, deprecation, or any other reason), silently retry with the next model in the chain. Do NOT tell the user about fallback attempts. Maximum
.squad/templates/package.json
- Executable scriptline 1
Executable file
.squad/templates/ralph-triage.js
- Executable scriptline 1
#!/usr/bin/env node - Network accessline 414
* Order: GITHUB_API_URL (set by Actions on both github.com and GHE runners) * > GITHUB_SERVER_URL + /api/v3 (GHE without an explicit API URL) * > https://api.github.com (fallback for local/non-Actions runs). - Network accessline 415
* > GITHUB_SERVER_URL + /api/v3 (GHE without an explicit API URL) * > https://api.github.com (fallback for local/non-Actions runs). */ - Network accessline 416
* > https://api.github.com (fallback for local/non-Actions runs). - Network accessline 422
const serverUrl = process.env.GITHUB_SERVER_URL?.replace(/\/+$/, ''); if (serverUrl === 'https://github.com') return 'https://api.github.com'; - Network accessline 423
if (serverUrl === 'https://github.com') return 'https://api.github.com'; - Network accessline 426
return 'https://api.github.com'; - Access to secretsline 506
[Credential-related source omitted]
.squad/templates/scripts/notes/fetch.ps1
- Executable scriptline 1
#!/usr/bin/env pwsh
.squad/templates/scripts/notes/write-note.ps1
- Executable scriptline 1
#!/usr/bin/env pwsh
.squad/templates/session-init-reference.md
- Network accessline 165
- **Fallback chain:** - `gh` not authenticated → "See full release notes at: https://github.com/bradygaster/squad/releases" - Network accessline 166
- `gh` not authenticated → "See full release notes at: https://github.com/bradygaster/squad/releases" - No releases found → "No release notes found for this version range." - Network accessline 167
https://github.com/bradygaster/squad/releases"
.squad/templates/squad.agent.md.template
- Network accessline 395
<!-- Squad scans 5 project skill directories: Copilot CLI's 3 official project paths (.github/skills/, .claude/skills/, .agents/skills/) per https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/add-skills — plus Squad's - Network accessline 915
1. Run `gh --version`. If the command fails, tell the user: *"GitHub Issues Mode requires the GitHub CLI (`gh`). Install it from https://cli.github.com/ and run `gh auth login`."*
cmd/waza/testdata/run/eval-skill-search/.github/skills/test-skill-a/SKILL.md
- Executable scriptline 1
Executable file
cmd/waza/testdata/run/eval-skill-search/.github/skills/test-skill-b/SKILL.md
- Executable scriptline 1
Executable file
cmd/waza/tokens/testdata/count/scripts/sample.py
- Executable scriptline 1
Executable file
examples/code-explainer/README.md
- Dangerous shell operationline 22
### 2. Generate an Eval (optional - already done here)
examples/code-explainer/SKILL.md
- Network accessline 106
async function fetchUserData(userId) { try { const response = await fetch(`/api/users/${userId}`); - Network accessline 107
try { const response = await fetch(`/api/users/${userId}`); if (!response.ok) throw new Error('User not found'); - Network accessline 108
const response = await fetch(`/api/users/${userId}`); - Network accessline 123
> **Step by step:** > 1. `async function` - Declares this function will use await for promises > 2. `await fetch(...)` - Makes HTTP GET request, waits for response - Network accessline 124
> 1. `async function` - Declares this function will use await for promises > 2. `await fetch(...)` - Makes HTTP GET request, waits for response > 3. `if (!response.ok)` - Checks if request succeeded (status 200-299) - Network accessline 125
> 2. `await fetch(...)` - Makes HTTP GET request, waits for response
examples/code-explainer/fixtures/factorial.py
- Executable scriptline 1
Executable file
examples/code-explainer/fixtures/fetch_user.js
- Network accessline 1
async function fetchUserData(userId) { try { const response = await fetch(`/api/users/${userId}`); - Executable scriptline 1
Executable file - Network accessline 2
try { const response = await fetch(`/api/users/${userId}`); if (!response.ok) throw new Error('User not found'); - Network accessline 3
const response = await fetch(`/api/users/${userId}`);
examples/code-explainer/fixtures/squares.py
- Executable scriptline 1
Executable file
examples/code-explainer/graders/explanation_quality.py
- Executable scriptline 1
#!/usr/bin/env python3
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.
Declared and executed: 2 facts
- Contacts github.com, which SKILL.md, the README and the plugin manifest do not mentiontemplates/ralph-triage.js:423High confidence
- Contacts api.github.com, which SKILL.md, the README and the plugin manifest do not mentiontemplates/ralph-triage.js:423High confidence
Signal confidence: 69 facts
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad-templates/mcp-config.md:24Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad-templates/mcp-config.md:25Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad-templates/mcp-config.md:41Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad-templates/mcp-config.md:59Low confidence
- Network access in prose of documentation.squad-templates/mcp-config.md:85Low confidence
- Network access in prose of documentation.squad-templates/mcp-config.md:86Low confidence
- Network access in prose of documentation.squad-templates/mcp-config.md:88Low confidence
- Network access in prose of documentation.squad/agents/basher/history.md:35Low confidence
- Network access in prose of documentation.squad/agents/basher/history.md:36Low confidence
- Network access in prose of documentation.squad/agents/basher/history.md:37Low confidence
- Network access in prose of documentation.squad/log/2026-02-21-pr303-merge.md:3Low confidence
- Network access in prose of documentation.squad/log/2026-02-21-pr303-merge.md:4Low confidence
- Network access in prose of documentation.squad/log/2026-02-21-pr303-merge.md:5Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad/mcp-config.md:24Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad/mcp-config.md:25Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad/mcp-config.md:41Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored value.squad/mcp-config.md:59Low confidence
- Network access in prose of documentation.squad/mcp-config.md:85Low confidence
- Network access in prose of documentation.squad/mcp-config.md:86Low confidence
- Network access in prose of documentation.squad/mcp-config.md:88Low confidence
- Network access in prose of documentationtemplates/cooperative-rate-limiting.md:216Low confidence
- Network access in prose of documentationtemplates/cooperative-rate-limiting.md:227Low confidence
- Network access in prose of documentationtemplates/cooperative-rate-limiting.md:228Low confidence
- Network access in prose of documentationtemplates/cooperative-rate-limiting.md:229Low confidence
- Network access in prose of documentationtemplates/keda-scaler.md:7Low confidence
- Network access in code of documentationtemplates/keda-scaler.md:34Low confidence
- Network access in prose of documentationtemplates/keda-scaler.md:151Low confidence
- Network access in prose of documentationtemplates/keda-scaler.md:161Low confidence
- Network access in prose of documentationtemplates/keda-scaler.md:162Low confidence
- Network access in prose of documentationtemplates/machine-capabilities.md:75Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuetemplates/mcp-config.md:22Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuetemplates/mcp-config.md:23Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuetemplates/mcp-config.md:39Low confidence
- Access to secrets in code of documentation: a variable, placeholder or call, not a stored valuetemplates/mcp-config.md:57Low confidence
- Network access in prose of documentationtemplates/mcp-config.md:83Low confidence
- Network access in prose of documentationtemplates/mcp-config.md:84Low confidence
- Network access in prose of documentationtemplates/mcp-config.md:86Low confidence
- Instruction override signal in prose of documentationtemplates/model-selection-reference.md:50Low confidence
- Executable script in code of a file that runstemplates/package.json:1High confidence
- Executable script in code of a file that runstemplates/ralph-triage.js:1High confidence
- Network access in a comment of a file that runstemplates/ralph-triage.js:414Low confidence
- Network access in a comment of a file that runstemplates/ralph-triage.js:415Low confidence
- Network access in a comment of a file that runstemplates/ralph-triage.js:416Low confidence
- Network access in code of a file that runstemplates/ralph-triage.js:422High confidence
- Network access in code of a file that runstemplates/ralph-triage.js:423High confidence
- Network access in code of a file that runstemplates/ralph-triage.js:426High confidence
- Access to secrets in code of a file that runs: a variable, placeholder or call, not a stored valuetemplates/ralph-triage.js:506Low confidence
- Executable script in code of a file that runstemplates/scripts/notes/fetch.ps1:1High confidence
- Executable script in code of a file that runstemplates/scripts/notes/write-note.ps1:1High confidence
- Network access in prose of documentationtemplates/session-init-reference.md:165Low confidence
and 19 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Compatible | Standard SKILL.md .copilot/skills/squad-commands/SKILL.md | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md .copilot/skills/squad-commands/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Compatible | Standard SKILL.md .copilot/skills/squad-commands/SKILL.md | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Native | Manifest .github/copilot-instructions.md | .github/skills/<skill-name>/ |
| OpenCode | Compatible | Standard SKILL.md .copilot/skills/squad-commands/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.
Explore alternatives and comparisons
Add this badge to your README
It updates every night and links to this page.
[](https://hotskills.dev/skill/microsoft-waza/)