#12 by GitHub stars
addyosmani/agent-skills
Production-grade engineering skills for AI coding agents.
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
skills/api-and-interface-design/SKILL.md
Week of Nov 2, 2026 · +3 / −1 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 199 return res.status(422).json({ error: 'idempotency key reused with a different payload' });
+ 199 return res.status(422).json({
+ 200 error: { code: 'IDEMPOTENCY_KEY_REUSED', message: 'Idempotency key reused with a different payload' },
+ 201 });
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/browser-testing-with-devtools/SKILL.md
Week of Nov 2, 2026 · +2 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
+ 139
+ 140 After a viewport or font change, measure layout only after fonts and resize observers have settled.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/ci-cd-and-automation/SKILL.md
Week of Nov 2, 2026 · +7 / −4 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 187 Lint failure → Agent runs `npm run lint --fix` and commits
+ 187 Lint failure → Agent runs `npm run lint -- --fix` and commits
+ 266 env:
+ 267 VERSION: ${{ inputs.version }}
- 267 # Deploy the specified previous version
- 268 npx vercel rollback ${{ inputs.version }}
+ 269 # Deploy the specified previous version. Pass the input through env,
+ 270 # never interpolate it into the script (shell injection).
+ 271 npx vercel rollback "$VERSION"
- 316 │ └── Use actions/cache or setup-node cache option for node_modules
+ 319 │ └── Use the setup-node cache option (or actions/cache) for the package manager cache, not node_modules
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/code-review-and-quality/SKILL.md
Week of Nov 2, 2026 · +2 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
+ 180
+ 181 Before reporting a finding, check it against the callers, guards and tests that reach the changed code, and drop it if they rule it out. Label defects that already exist in the base separately from regressions this change introduces. Zero findings is a valid result; do not invent one.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/code-simplification/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 3 description: Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity.
+ 3 description: Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity. Use when asked to simplify, clean up, or reduce the nesting of a function or module that already works, even when the code is pasted inline and nothing else needs to change.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/constraint-driven-development/SKILL.md
Week of Nov 2, 2026 · +18 / −10 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 116 | Secrets | No secrets in source | `gitleaks detect --redact` | every edit |
+ 116 | Secrets | No secrets in source | `gitleaks dir . --redact` | every edit |
- 118 | Security: code | No high findings | `semgrep scan --config p/default` | CI |
+ 118 | Security: code | Nothing at high or above | `npm run check:security` | CI |
- 120 | Accessibility | Zero critical or serious | `axe $PREVIEW_URL --tags wcag2a,wcag2aa,wcag21aa` | preview deploy |
+ 120 | Accessibility | Zero critical or serious | `npm run check:a11y` | preview deploy |
- 151 | Coverage (JS) | your test runner | already there | `vitest run --coverage` (or `jest --coverage`) | coverage of changed lines |
+ 151 | Coverage (JS) | your test runner | Vitest: `npm i -D @vitest/coverage-v8`; Jest: already there | `vitest run --coverage` (or `jest --coverage`) | coverage of changed lines |
- 153 | Security: code | Semgrep | `pipx install semgrep` | `semgrep scan --config p/default --config p/owasp-top-ten` | any high finding |
- 154 | Security: secrets | gitleaks | `brew install gitleaks` | `gitleaks detect --redact --no-banner` | any finding |
+ 153 | Security: code | Semgrep | `pipx install semgrep` | `npm run check:security` (below) | high or critical, including legacy `ERROR` |
+ 154 | Security: secrets | gitleaks | `brew install gitleaks` | `gitleaks dir . --redact --no-banner` | any finding |
- 158 | Accessibility | axe-core | `npm i -D @axe-core/cli` | `axe $URL --tags wcag2a,wcag2aa,wcag21aa` | zero critical or serious |
+ 158 | Accessibility | axe-core | `npm i -D @axe-core/cli` | `npm run check:a11y` (below) | zero critical or serious |
+ 170 `semgrep scan` and `axe` can exit 0 on findings; copy [scripts/quality-gate.mjs](scripts/quality-gate.mjs) into the project's `scripts/` directory to enforce these thresholds.
+ 171 Keep the scanner before `&&` so a failed scan stops the command.
+ 172
- 175 "check:fast": "tsc --noEmit && eslint . && gitleaks detect --redact --no-banner",
+ 178 "check:fast": "tsc --noEmit && eslint . && gitleaks dir . --redact --no-banner",
- 177 "check:full": "npm run check:task && semgrep scan --config p/default && osv-scanner scan source -r ."
+ 180 "check:security": "semgrep scan --config p/default --strict --json > semgrep-results.json && node scripts/quality-gate.mjs semgrep semgrep-results.json",
+ 181 "check:a11y": "axe \"$PREVIEW_URL\" --tags wcag2a,wcag2aa,wcag21aa --stdout > axe-results.json && node scripts/quality-gate.mjs axe axe-results.json",
+ 182 "check:full": "npm run check:task && npm run check:security && osv-scanner scan source -r ."
- 182 That mapping matters more than the tools. `check:fast` is what runs after an edit, `check:task` when the agent thinks it's done, `check:full` in CI.
+ 187 That mapping matters more than the tools. `check:fast` is what runs after an edit, `check:task` when the agent thinks it's done, `check:full` in CI. Run `check:a11y` after the preview is reachable, with `PREVIEW_URL` set (the example uses POSIX shell syntax).
+ 188
+ 189 Before calling any row enforced, run its actual CI command against a known violation and a clean control. Confirm that the violation fails, the control passes, and scanner errors fail too. For a severity threshold, also confirm a below-threshold finding passes. Apply this to every dimension, including coverage and Lighthouse: generating a report alone does not enforce the number in `CONSTRAINTS.md`.
+ 310 - [ ] Each enforced command fails on a deliberate violation and scanner error, passes a clean control, and preserves the agreed severity threshold
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/context-engineering/SKILL.md
Week of Nov 2, 2026 · +3 / −3 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 53 - Lint: `npm run lint --fix`
+ 53 - Lint: `npm run lint -- --fix`
- 202 **Start trimming at 75% capacity, not 100%.** By the time the window is genuinely full, the model's attention is already fragmented across too many signals. The 75% threshold gives room to compress gracefully rather than cut desperately mid-task.
+ 202 **Compact well before the host's limit; the threshold varies by host.** By the time the window is genuinely full, the model's attention is already fragmented across too many signals. The margin gives room to compress gracefully rather than cut desperately mid-task.
- 324 | Context cliff | Waiting until the window is full before managing it — attention fragments and output quality drops abruptly at the limit | Start trimming at 75% capacity; compress rather than cut |
+ 324 | Context cliff | Waiting until the window is full before managing it — attention fragments and output quality drops abruptly at the limit | Compact well before the host's limit; compress rather than cut |
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/debugging-and-error-recovery/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 84 npm test -- --testPathPattern="specific-file" --runInBand
+ 84 npm test -- specific-file --runInBand
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/deprecation-and-migration/SKILL.md
Week of Nov 2, 2026 · +6 / −1 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
+ 148
+ 149 // Translate the new shape back into what old consumers expect
+ 150 private toOldFormat(task: Task): OldTask {
+ 151 return { id: Number(task.id), title: task.title, done: task.status === 'done' };
+ 152 }
- 160 return new LegacyTaskService();
+ 165 return new OldTaskService();
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/documentation-and-adrs/SKILL.md
Week of Nov 2, 2026 · +3 / −2 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 114 // Rate limit uses a sliding window — reset counter at window boundary,
- 115 // not on a fixed schedule, to prevent burst attacks at window edges
+ 114 // Rate limit uses a fixed window that opens on the first request after the
+ 115 // previous one expires, not on a clock schedule. Known gap: a client can spend
+ 116 // the full limit just before a reset and again just after (2x in a moment)
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/doubt-driven-development/SKILL.md
Week of Nov 2, 2026 · +2 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
+ 84
+ 85 Strip reasoning, not evidence: if a caller, guard or test contradicts the claim, include it in the unit.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/frontend-ui-engineering/SKILL.md
Week of Nov 2, 2026 · +6 / −6 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 82 const { tasks, isLoading, error, refetch } = useTasks();
+ 82 const { tasks, isLoading, error, refetch, toggleTask, deleteTask } = useTasks();
- 88 return <TaskList tasks={tasks} />;
+ 88 return <TaskList tasks={tasks} onToggle={toggleTask} onDelete={deleteTask} />;
- 92 export function TaskList({ tasks }: { tasks: Task[] }) {
+ 92 export function TaskList({ tasks, onToggle, onDelete }: { tasks: Task[] } & Pick<TaskItemProps, 'onToggle' | 'onDelete'>) {
- 95 {tasks.map(task => <TaskItem key={task.id} task={task} />)}
+ 95 {tasks.map(task => <TaskItem key={task.id} task={task} onToggle={onToggle} onDelete={onDelete} />)}
- 237 function TaskList({ tasks }: { tasks: Task[] }) {
+ 237 function TaskList({ tasks, onCreateTask }: { tasks: Task[]; onCreateTask: () => void }) {
- 275 <div className="space-y-3" aria-busy="true" aria-label="Loading tasks">
+ 275 <div className="space-y-3" role="status" aria-busy="true" aria-label="Loading tasks">
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/git-workflow-and-versioning/SKILL.md
Week of Nov 2, 2026 · +3 / −3 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 3 description: Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog.
+ 3 description: Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog. Use when asked to write a commit message or a changelog entry for a change, or to split a change into commits, even when the diff is pasted inline and the message seems easy to write from it.
- 219 # 2. Ensure no secrets
- 220 git diff --staged | grep -i "password\|secret\|api_key\|token"
+ 219 # 2. Ensure no secrets (lists matching file names only — any output means review them)
+ 220 git diff --staged -i -G'password|secret|api_key|token' --name-only
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/idea-refine/SKILL.md
Week of Nov 2, 2026 · +4 / −2 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 31 # Optional: Initialize the ideas directory
- 32 bash skills/idea-refine/scripts/idea-refine.sh
+ 31 # Optional. Run from the project root so this creates ./docs/ideas.
+ 32 # <skill-dir> is the directory that contains this SKILL.md
+ 33 # (for example .agents/skills/idea-refine or .cursor/skills/idea-refine).
+ 34 bash <skill-dir>/scripts/idea-refine.sh
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/incremental-implementation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/interview-me/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/observability-and-instrumentation/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/performance-optimization/SKILL.md
Week of Nov 2, 2026 · +2 / −2 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 208 # Lighthouse CI
- 209 npx lhci autorun
+ 208 # Lighthouse CI. The CLI package is @lhci/cli; unscoped `lhci` on npm is not it.
+ 209 npx --package=@lhci/cli lhci autorun
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/planning-and-task-breakdown/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/security-and-hardening/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 3 description: Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.
+ 3 description: Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions or session cookies, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/shipping-and-launch/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 192 class ErrorBoundary extends React.Component {
+ 192 class ErrorBoundary extends React.Component<React.PropsWithChildren> {
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/source-driven-development/SKILL.md
Week of Nov 2, 2026 · +3 / −2 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 161 "useTransition now supports async functions [...] to handle
- 162 pending states automatically"
+ 161 "In React 19, we're adding support for using async functions in
+ 162 transitions to handle pending states, errors, forms, and optimistic
+ 163 updates automatically."
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/spec-driven-development/SKILL.md
Week of Nov 2, 2026 · +1 / −1 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
- 92 Lint: npm run lint --fix
+ 92 Lint: npm run lint -- --fix
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/test-driven-development/SKILL.md
Week of Nov 2, 2026 · +2 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
+ 248 For crash or rollback behavior, exercise the real boundary: an injected exception is not process termination, and a mocked transaction call is not a database rollback.
+ 249
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
skills/using-agent-skills/SKILL.md
Week of Nov 2, 2026 · +0 / −0 lines
Before Network or broad shell → After Network or broad shell
aeac41d4d005 → 301b02b12bff
Week of Oct 26, 2026 · Line counts unavailable
Before Not checked yet → After Network or broad shell
First observation → aeac41d4d005
No earlier version was observed for comparison.
Verified commit 301b02b12bff98e4688e6984af6556802322bbde
git clone --filter=blob:none --no-checkout https://github.com/addyosmani/agent-skills.git .hotskills/addyosmani-agent-skills && git -C .hotskills/addyosmani-agent-skills checkout --detach 301b02b12bff98e4688e6984af6556802322bbde
# Copy each selected skill directory from .hotskills/addyosmani-agent-skills into .claude/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/addyosmani/agent-skills.git .hotskills/addyosmani-agent-skills && git -C .hotskills/addyosmani-agent-skills checkout --detach 301b02b12bff98e4688e6984af6556802322bbde
# Copy each selected skill directory from .hotskills/addyosmani-agent-skills into .agents/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/addyosmani/agent-skills.git .hotskills/addyosmani-agent-skills && git -C .hotskills/addyosmani-agent-skills checkout --detach 301b02b12bff98e4688e6984af6556802322bbde
# Copy each selected skill directory from .hotskills/addyosmani-agent-skills into .gemini/skills/<skill-name>/git clone --filter=blob:none --no-checkout https://github.com/addyosmani/agent-skills.git .hotskills/addyosmani-agent-skills && git -C .hotskills/addyosmani-agent-skills checkout --detach 301b02b12bff98e4688e6984af6556802322bbde
# Copy each selected skill directory from .hotskills/addyosmani-agent-skills into .opencode/skills/<skill-name>/Heat
7.5- Star growth, last 7 daysAhead of 88% of tracked repositories
- Star growth, last 24 hoursAhead of 86% of tracked repositories
- Rank movement, last 7 daysAhead of 72% of tracked repositories
- Commits, last 30 daysAhead of 96% 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
- api-and-interface-design
skills/api-and-interface-design - browser-testing-with-devtools
skills/browser-testing-with-devtools - ci-cd-and-automation
skills/ci-cd-and-automation - code-review-and-quality
skills/code-review-and-quality - code-simplification
skills/code-simplification - constraint-driven-development
skills/constraint-driven-development - context-engineering
skills/context-engineering - debugging-and-error-recovery
skills/debugging-and-error-recovery - deprecation-and-migration
skills/deprecation-and-migration - documentation-and-adrs
skills/documentation-and-adrs - doubt-driven-development
skills/doubt-driven-development - frontend-ui-engineering
skills/frontend-ui-engineering - git-workflow-and-versioning
skills/git-workflow-and-versioning - idea-refine
skills/idea-refine - incremental-implementation
skills/incremental-implementation - interview-me
skills/interview-me - observability-and-instrumentation
skills/observability-and-instrumentation - performance-optimization
skills/performance-optimization - planning-and-task-breakdown
skills/planning-and-task-breakdown - security-and-hardening
skills/security-and-hardening - shipping-and-launch
skills/shipping-and-launch - source-driven-development
skills/source-driven-development - spec-driven-development
skills/spec-driven-development - test-driven-development
skills/test-driven-development - using-agent-skills
skills/using-agent-skills
How it works
api-and-interface-design
When your agent uses it
Guides stable API and interface design. Use when designing APIs, module boundaries, or any public interface. Use when creating REST or GraphQL endpoints, defining type contracts between modules, or establishing boundaries between frontend and backend.
What it loads into context
Frontmatter
52 tokensAlways available to the agent
SKILL.md
3,311 tokensWhen the skill is activated
Reference documents
93,341 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Core Principles
- REST API Patterns
- TypeScript Interface Patterns
- Common Rationalizations
- Red Flags
- Verification
Scripts executed separately
../constraint-driven-development/scripts/quality-gate.mjs../idea-refine/scripts/idea-refine.sh
Files
../../.claude-plugin/marketplace.jsonasset857 bytes../../.claude-plugin/plugin.jsonasset517 bytes../../.claude/commands/build.mddoc3,990 bytes../../.claude/commands/code-simplify.mddoc1,099 bytes../../.claude/commands/constraints.mddoc2,793 bytes../../.claude/commands/plan.mddoc836 bytes../../.claude/commands/review.mddoc879 bytes../../.claude/commands/ship.mddoc4,631 bytes../../.claude/commands/spec.mddoc944 bytes../../.claude/commands/test.mddoc696 bytes../../.claude/commands/webperf.mddoc2,005 bytes../../.claude/commands/webperf.mddoc2,005 bytes../../commands/build.tomlasset3,840 bytes../../commands/code-simplify.tomlasset1,066 bytes../../commands/constraints.tomlasset2,775 bytes../../commands/planning.tomlasset804 bytes../../commands/review.tomlasset846 bytes../../commands/ship.tomlasset4,711 bytes../../commands/spec.tomlasset911 bytes../../commands/test.tomlasset650 bytes../../commands/webperf.tomlasset2,031 bytes../../commands/webperf.tomlasset2,031 bytesSKILL.mdcore14,938 bytes../browser-testing-with-devtools/SKILL.mddoc14,640 bytes../ci-cd-and-automation/SKILL.mddoc11,512 bytes../code-review-and-quality/SKILL.mddoc21,263 bytes../code-simplification/SKILL.mddoc13,719 bytes../constraint-driven-development/SKILL.mddoc22,216 bytes../constraint-driven-development/references/floor-guard.mddoc10,701 bytes../constraint-driven-development/scripts/quality-gate.mjsruns1,927 bytes../context-engineering/SKILL.mddoc15,514 bytes../debugging-and-error-recovery/SKILL.mddoc10,893 bytes../deprecation-and-migration/SKILL.mddoc12,839 bytes../documentation-and-adrs/SKILL.mddoc10,999 bytes../doubt-driven-development/SKILL.mddoc16,753 bytes../frontend-ui-engineering/SKILL.mddoc11,950 bytes../git-workflow-and-versioning/SKILL.mddoc14,403 bytes../idea-refine/SKILL.mddoc9,404 bytes../idea-refine/examples.mddoc20,284 bytes../idea-refine/frameworks.mddoc5,404 bytes../idea-refine/refinement-criteria.mddoc5,738 bytes../idea-refine/scripts/idea-refine.shruns342 bytes../incremental-implementation/SKILL.mddoc9,629 bytes../interview-me/SKILL.mddoc15,080 bytes../observability-and-instrumentation/SKILL.mddoc13,948 bytes../performance-optimization/SKILL.mddoc16,783 bytes../performance-optimization/references/optimization-patterns.mddoc9,692 bytes../planning-and-task-breakdown/SKILL.mddoc10,564 bytes../security-and-hardening/SKILL.mddoc17,578 bytes../security-and-hardening/references/hardening-patterns.mddoc13,352 bytes../shipping-and-launch/SKILL.mddoc11,540 bytes../source-driven-development/SKILL.mddoc10,104 bytes../spec-driven-development/SKILL.mddoc13,099 bytes../test-driven-development/SKILL.mddoc16,845 bytes../using-agent-skills/SKILL.mddoc10,446 bytes
Read SKILL.md
# API and Interface Design
## Overview
Design stable, well-documented interfaces that are hard to misuse. Good interfaces make the right thing easy and the wrong thing hard. This applies to REST APIs, GraphQL schemas, module boundaries, component props, and any surface where one piece of code talks to another.
## When to Use
- Designing new API endpoints
- Defining module boundaries or contracts between teams
- Creating component prop interfaces
- Establishing database schema that informs API shape
- Changing existing public interfaces
View the complete source on GitHubbrowser-testing-with-devtools
When your agent uses it
Tests in real browsers via Chrome DevTools MCP. Use when building or debugging anything that runs in a browser. Use when you need to inspect the DOM, capture console errors, analyze network requests, profile performance, or verify visual output with real runtime data. Requires the chrome-devtools MCP server to be configured.
What it loads into context
Frontmatter
72 tokensAlways available to the agent
SKILL.md
3,107 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
- Overview
- When to Use
- Setting Up Chrome DevTools MCP
- Security Boundaries
- The DevTools Debugging Workflow
- Writing Test Plans for Complex UI Bugs
- Screenshot-Based Verification
- Console Analysis Patterns
- Accessibility Verification with DevTools
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore14,640 bytesSKILL.mdcore14,640 bytes
Read SKILL.md
# Browser Testing with DevTools
## Overview
Use Chrome DevTools MCP to give your agent eyes into the browser. This bridges the gap between static code analysis and live browser execution — the agent can see what the user sees, inspect the DOM, read console logs, analyze network requests, and capture performance data. Instead of guessing what's happening at runtime, verify it.
## When to Use
- Building or modifying anything that renders in a browser
- Debugging UI issues (layout, styling, interaction)
- Diagnosing console errors or warnings
- Analyzing network requests and API responses
- Profiling performance (Core Web Vitals, paint timing, layout shifts)
- Verifying that a fix actually works in the browserView the complete source on GitHubci-cd-and-automation
When your agent uses it
Automates CI/CD pipeline setup. Use when setting up or modifying build and deployment pipelines. Use when you need to automate quality gates, configure test runners in CI, or establish deployment strategies.
What it loads into context
Frontmatter
49 tokensAlways available to the agent
SKILL.md
2,756 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
- Overview
- When to Use
- The Quality Gate Pipeline
- GitHub Actions Configuration
- Feeding CI Failures Back to Agents
- Deployment Strategies
- Environment Management
- Automation Beyond CI
- CI Optimization
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore11,512 bytesSKILL.mdcore11,512 bytes
Read SKILL.md
# CI/CD and Automation
## Overview
Automate quality gates so that no change reaches production without passing tests, lint, type checking, and build. CI/CD is the enforcement mechanism for every other skill — it catches what humans and agents miss, and it does so consistently on every single change.
**Shift Left:** Catch problems as early in the pipeline as possible. A bug caught in linting costs minutes; the same bug caught in production costs hours. Move checks upstream — static analysis before tests, tests before staging, staging before production.
**Faster is Safer:** Smaller batches and more frequent releases reduce risk, not increase it. A deployment with 3 changes is easier to debug than one with 30. Frequent releases build confidence in the release process itself.
## When to Use
- Setting up a new project's CI pipeline
- Adding or modifying automated checksView the complete source on GitHubcode-review-and-quality
When your agent uses it
Conducts multi-axis code review. Use before merging any change. Use when reviewing code written by yourself, another agent, or a human. Use when you need to assess code quality across multiple dimensions before it enters the main branch. Use when asked to review a diff or a pull request, even when the diff is pasted inline.
What it loads into context
Frontmatter
75 tokensAlways available to the agent
SKILL.md
4,509 tokensWhen the skill is activated
Reference documents
6,649 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Five-Axis Review
- Structural Remedies
- Change Sizing
- Change Descriptions
- Review Process
- Multi-Model Review Pattern
- Dead Code Hygiene
- Review Speed
- Handling Disagreements
- Honesty in Review
- Dependency Discipline
- The Review Checklist
- See Also
- Common Rationalizations
- Red Flags
- Verification
Files
../../references/performance-checklist.mddoc13,292 bytes../../references/security-checklist.mddoc14,503 bytesSKILL.mdcore21,263 bytes
Read SKILL.md
# Code Review and Quality
## Overview
Multi-dimensional code review with quality gates. Every change gets reviewed before merge — no exceptions. Review covers five axes: correctness, readability, architecture, security, and performance.
**The approval standard:** Approve a change when it definitely improves overall code health, even if it isn't perfect. Perfect code doesn't exist — the goal is continuous improvement. Don't block a change because it isn't exactly how you would have written it. If it improves the codebase and follows the project's conventions, approve it.
## When to Use
- Before merging any PR or change
- After completing a feature implementation
- When another agent or model produced code you need to evaluate
- When refactoring existing codeView the complete source on GitHubcode-simplification
When your agent uses it
Simplifies code for clarity. Use when refactoring code for clarity without changing behavior. Use when code works but is harder to read, maintain, or extend than it should be. Use when reviewing code that has accumulated unnecessary complexity. Use when asked to simplify, clean up, or reduce the nesting of a function or module that already works, even when the code is pasted inline and nothing else needs to change.
What it loads into context
Frontmatter
91 tokensAlways available to the agent
SKILL.md
3,036 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
- Overview
- When to Use
- The Five Principles
- The Simplification Process
- Language-Specific Guidance
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore13,719 bytesSKILL.mdcore13,719 bytes
Read SKILL.md
# Code Simplification
> Inspired by the [Claude Code Simplifier plugin](https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md). Adapted here as a model-agnostic, process-driven skill for any AI coding agent.
## Overview
Simplify code by reducing complexity while preserving exact behavior. The goal is not fewer lines — it's code that is easier to read, understand, modify, and debug. Every simplification must pass a simple test: "Would a new team member understand this faster than the original?"
## When to Use
- After a feature is working and tests pass, but the implementation feels heavier than it needs to be
- During code review when readability or complexity issues are flagged
- When you encounter deeply nested logic, long functions, or unclear names
- When refactoring code written under time pressureView the complete source on GitHubconstraint-driven-development
When your agent uses it
Establishes a project's quality bar as a written contract and stops agents quietly lowering it. Interviews the user on which dimensions matter, supplies sane default thresholds when they have no number in mind, records everything in CONSTRAINTS.md, and watches the diff for a weakened bar — new @ts-ignore or eslint-disable suppressions, skipped or deleted tests, assertions stripped out, unimplemented stubs, thresholds edited down. Use when no quality bar is written down, when the user says "set up constraints" or "define our standards", when the user wants dimensions they care about — accessibility, web performance, coverage — set up as enforced constraints, when an agent keeps silencing checks or skipping tests to get to green, when you need a coverage or performance threshold and don't know what number to pick, or when an agent writes more code than anyone will read.
What it loads into context
Frontmatter
179 tokensAlways available to the agent
SKILL.md
5,247 tokensWhen the skill is activated
Reference documents
2,981 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Loading Constraints
- The Process
- Sane Defaults
- Escalation Path
- Common Rationalizations
- Red Flags
- Verification
- See Also
Scripts executed separately
scripts/quality-gate.mjs
Files
SKILL.mdcore22,216 bytesSKILL.mdcore22,216 bytesreferences/floor-guard.mddoc10,701 bytesscripts/quality-gate.mjsruns1,927 bytes
Read SKILL.md
# Constraint-Driven Development
## Overview
Other skills in this pack describe what good looks like. `code-review-and-quality` gives you five axes. `test-driven-development` gives you a cycle. `security-and-hardening` gives you a threat list. All of that lives in prose the agent reads and may or may not follow, and none of it survives the end of the session.
This skill produces something different: a written record of **this project's** bar, with numbers, that outlives the conversation and can be checked mechanically.
The reason matters. When you wrote the code, reading it told you whether it was any good. An agent writes more in an afternoon than you will read that week, so the judgement moves out of your head and into checks that run around the loop. Those checks need to exist, they need numbers you actually chose, and they need to fire close enough to the work that the agent fixes its own output.
Spec-driven development says what to build. Test-driven development proves it works. Constraint-driven development defines what "good enough to ship" means, before anyone argues about it in a pull request.
## When to Use
View the complete source on GitHubcontext-engineering
When your agent uses it
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
What it loads into context
Frontmatter
47 tokensAlways available to the agent
SKILL.md
3,218 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
- Overview
- When to Use
- The Context Hierarchy
- Context Packing Strategies
- Context Budget Management
- MCP Integrations
- Confusion Management
- Anti-Patterns
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore15,514 bytesSKILL.mdcore15,514 bytesSKILL.mdcore15,514 bytes
Read SKILL.md
# Context Engineering
## Overview
Feed agents the right information at the right time. Context is the single biggest lever for agent output quality — too little and the agent hallucinates, too much and it loses focus. Context engineering is the practice of deliberately curating what the agent sees, when it sees it, and how it's structured.
## When to Use
- Starting a new coding session
- Agent output quality is declining (wrong patterns, hallucinated APIs, ignoring conventions)
- Switching between different parts of a codebase
- Setting up a new project for AI-assisted development
- The agent is not following project conventions
View the complete source on GitHubdebugging-and-error-recovery
When your agent uses it
Guides systematic root-cause debugging. Use when tests fail, builds break, something that worked yesterday broke, behavior doesn't match expectations, or you encounter any unexpected error. Use when you need to figure out what broke and why — a systematic approach to finding and fixing the root cause rather than guessing.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
2,438 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
- Overview
- When to Use
- The Stop-the-Line Rule
- The Triage Checklist
- Error-Specific Patterns
- Safe Fallback Patterns
- Instrumentation Guidelines
- Common Rationalizations
- Treating Error Output as Untrusted Data
- Red Flags
- Verification
Files
SKILL.mdcore10,893 bytesSKILL.mdcore10,893 bytesSKILL.mdcore10,893 bytesSKILL.mdcore10,893 bytes
Read SKILL.md
# Debugging and Error Recovery
## Overview
Systematic debugging with structured triage. When something breaks, stop adding features, preserve evidence, and follow a structured process to find and fix the root cause. Guessing wastes time. The triage checklist works for test failures, build errors, runtime bugs, and production incidents.
## When to Use
- Tests fail after a code change
- The build breaks
- Runtime behavior doesn't match expectations
- A bug report arrives
- An error appears in logs or console
- Something worked before and stopped workingView the complete source on GitHubdeprecation-and-migration
When your agent uses it
Manages deprecation and migration. Use when removing old systems, APIs, or features. Use when migrating users from one implementation to another. Use when migrating a database schema in production, such as renaming or dropping a column without downtime (expand/contract). Use when deciding whether to maintain or sunset existing code.
What it loads into context
Frontmatter
73 tokensAlways available to the agent
SKILL.md
2,788 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
- Overview
- When to Use
- Core Principles
- The Deprecation Decision
- Compulsory vs Advisory Deprecation
- The Migration Process
- Migration Patterns
- Zombie Code
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore12,839 bytes
Read SKILL.md
# Deprecation and Migration
## Overview
Code is a liability, not an asset. Every line of code has ongoing maintenance cost — bugs to fix, dependencies to update, security patches to apply, and new engineers to onboard. Deprecation is the discipline of removing code that no longer earns its keep, and migration is the process of moving users safely from the old to the new.
Most engineering organizations are good at building things. Few are good at removing them. This skill addresses that gap.
## When to Use
- Replacing an old system, API, or library with a new one
- Sunsetting a feature that's no longer needed
- Consolidating duplicate implementations
- Removing dead code that nobody owns but everybody depends onView the complete source on GitHubdocumentation-and-adrs
When your agent uses it
Records decisions and documentation. Use when you need to document an architecture decision (ADR) or the reasoning behind a design choice, when changing public APIs, shipping features, or when you need to record context that future engineers and agents will need to understand the codebase.
What it loads into context
Frontmatter
62 tokensAlways available to the agent
SKILL.md
2,374 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
- Overview
- When to Use
- Architecture Decision Records (ADRs)
- Inline Documentation
- API Documentation
- README Structure
- Changelog Maintenance
- Documentation for Agents
- Prose Review
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore10,999 bytesSKILL.mdcore10,999 bytes
Read SKILL.md
# Documentation and ADRs
## Overview
Document decisions, not just code. The most valuable documentation captures the *why* — the context, constraints, and trade-offs that led to a decision. Code shows *what* was built; documentation explains *why it was built this way* and *what alternatives were considered*. This context is essential for future humans and agents working in the codebase.
## When to Use
- Making a significant architectural decision
- Choosing between competing approaches
- Adding or changing a public API
- Shipping a feature that changes user-facing behavior
- Onboarding new team members (or agents) to the project
- When you find yourself explaining the same thing repeatedlyView the complete source on GitHubdoubt-driven-development
When your agent uses it
Subjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later.
What it loads into context
Frontmatter
99 tokensAlways available to the agent
SKILL.md
3,640 tokensWhen the skill is activated
Reference documents
3,957 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Loading Constraints
- The Process
- Common Rationalizations
- Red Flags
- Interaction with Other Skills
- Verification
Files
../../references/orchestration-patterns.mddoc18,201 bytesSKILL.mdcore16,753 bytesSKILL.mdcore16,753 bytes
Read SKILL.md
# Doubt-Driven Development
## Overview
A confident answer is not a correct one. Long sessions accumulate context that quietly turns assumptions into "facts" without anyone noticing. Doubt-driven development is the discipline of materializing a fresh-context reviewer — biased to **disprove**, not approve — before any non-trivial output stands.
This is not `/review`. `/review` is a verdict on a finished artifact. This is an in-flight posture: non-trivial decisions get cross-examined while course-correction is still cheap.
## When to Use
A decision is **non-trivial** when at least one of these is true:
- It introduces or modifies branching logic
- It crosses a module or service boundaryView the complete source on GitHubfrontend-ui-engineering
When your agent uses it
Builds production-quality, accessible, responsive user-facing UIs. Use when building or modifying interfaces and pages, creating components, implementing layouts, meeting WCAG accessibility requirements, managing state, or when the output needs to look and feel production-quality rather than AI-generated.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
2,808 tokensWhen the skill is activated
Reference documents
1,346 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Component Architecture
- State Management
- Design System Adherence
- Accessibility (WCAG 2.1 AA)
- Responsive Design
- Loading and Transitions
- See Also
- Common Rationalizations
- Red Flags
- Verification
Files
../../references/accessibility-checklist.mddoc5,332 bytesSKILL.mdcore11,950 bytes
Read SKILL.md
# Frontend UI Engineering
## Overview
Build production-quality user interfaces that are accessible, performant, and visually polished. The goal is UI that looks like it was built by a design-aware engineer at a top company — not like it was generated by an AI. This means real design system adherence, proper accessibility, thoughtful interaction patterns, and no generic "AI aesthetic."
## When to Use
- Building new UI components or pages
- Modifying existing user-facing interfaces
- Implementing responsive layouts
- Adding interactivity or state management
- Fixing visual or UX issues
View the complete source on GitHubgit-workflow-and-versioning
When your agent uses it
Structures git workflow practices. Use when making any code change. Use when committing, branching, resolving conflicts, splitting uncommitted work in a messy working tree into clean atomic commits, opening or reviewing a pull request (PR), pushing to a remote, or when you need to organize work across multiple parallel streams. Use when cutting a release, choosing a semantic version bump, tagging, or writing a changelog. Use when asked to write a commit message or a changelog entry for a change, or to split a change into commits, even when the diff is pasted inline and the message seems easy to write from it.
What it loads into context
Frontmatter
135 tokensAlways available to the agent
SKILL.md
3,339 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
- Overview
- When to Use
- Core Principles
- Branching Strategy
- Working with Worktrees
- The Save Point Pattern
- Change Summaries
- Pre-Commit Hygiene
- Handling Generated Files
- Using Git for Debugging
- Release & Versioning
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore14,403 bytesSKILL.mdcore14,403 bytesSKILL.mdcore14,403 bytesSKILL.mdcore14,403 bytesSKILL.mdcore14,403 bytesSKILL.mdcore14,403 bytes
Read SKILL.md
# Git Workflow and Versioning
## Overview
Git is your safety net. Treat commits as save points, branches as sandboxes, and history as documentation. With AI agents generating code at high speed, disciplined version control is the mechanism that keeps changes manageable, reviewable, and reversible.
## When to Use
Always. Every code change flows through git.
## Core Principles
### Trunk-Based Development (Recommended)
View the complete source on GitHubidea-refine
When your agent uses it
Refines raw ideas into sharp, actionable concepts through structured divergent and convergent thinking. Use when an idea is still vague, when you need to stress-test assumptions before committing to a plan, or when you want to expand options before converging on one. Triggers on "ideate", "refine this idea", or "stress-test my plan".
What it loads into context
Frontmatter
79 tokensAlways available to the agent
SKILL.md
2,140 tokensWhen the skill is activated
Reference documents
6,731 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- How It Works
- Usage
- Output
- Detailed Instructions
- Common Rationalizations
- Red Flags
- Verification
Scripts executed separately
scripts/idea-refine.sh
Files
SKILL.mdcore9,404 bytesSKILL.mdcore9,404 bytesexamples.mddoc20,284 bytesframeworks.mddoc5,404 bytesrefinement-criteria.mddoc5,738 bytesscripts/idea-refine.shruns342 bytes
Read SKILL.md
# Idea Refine
## Overview
Refines raw ideas into sharp, actionable concepts worth building through structured divergent and convergent thinking.
## When to Use
- Use when an idea is still vague and needs shaping before it can become a plan
- Use when you need to stress-test assumptions before committing to a direction
- Use when you want to expand options before converging on one
- Trigger phrases: "Help me refine this idea", "Ideate on [concept]", "Stress-test my plan"
- Not for: a user who is unsure what they want at all (use `interview-me`), or a direction already chosen that needs a spec (use `spec-driven-development`)
View the complete source on GitHubincremental-implementation
When your agent uses it
Delivers changes incrementally in thin, verifiable slices. Use when implementing any feature or change that touches more than one file, or when picking up the next task from a plan. Use when rolling a change out behind a feature flag, when you're about to write a large amount of code at once, or when a task feels too big to land in one step.
What it loads into context
Frontmatter
82 tokensAlways available to the agent
SKILL.md
2,068 tokensWhen the skill is activated
Reference documents
827 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Increment Cycle
- Slicing Strategies
- Implementation Rules
- Working with Agents
- Increment Checklist
- Common Rationalizations
- Red Flags
- Verification
- See Also
Files
../../references/definition-of-done.mddoc3,798 bytesSKILL.mdcore9,629 bytes
Read SKILL.md
# Incremental Implementation
## Overview
Build in thin vertical slices — implement one piece, test it, verify it, then expand. Avoid implementing an entire feature in one pass. Each increment should leave the system in a working, testable state. This is the execution discipline that makes large features manageable.
## When to Use
- Implementing any multi-file change
- Building a new feature from a task breakdown
- Refactoring existing code
- Any time you're tempted to write more than ~100 lines before testing
**When NOT to use:** Single-file, single-function changes where the scope is already minimal.View the complete source on GitHubinterview-me
When your agent uses it
Extracts what the user actually wants instead of what they think they should want. Achieves this through one-question-at-a-time interview until ~95% confidence about the underlying intent. Use when an ask is underspecified ("build me X" without "for whom" or "why now"), when the user explicitly invokes ("interview me", "grill me", "are we sure?", "stress-test my thinking"), or when you catch yourself silently filling in ambiguous requirements before any plan, spec, or code exists.
What it loads into context
Frontmatter
111 tokensAlways available to the agent
SKILL.md
3,383 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
- Overview
- When to Use
- Loading Constraints
- The Process
- Output
- Example
- Interaction with Other Skills
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore15,080 bytes
Read SKILL.md
# Interview Me
## Overview
What people ask for and what they actually want are different things. They ask for "a dashboard" because that's what one asks for, not because a dashboard solves their problem. They say "make it faster" without a number to hit.
The cheapest moment to find this gap is before any plan, spec, or code exists. Once you've started building, switching costs are real, and the user will rationalize the wrong thing into a "good enough" thing. The misfit gets locked in.
This skill closes the gap before it costs anything. The other Define-phase skills assume you already know roughly what you want: `idea-refine` generates variations from an idea, `spec-driven-development` writes the requirements down, `doubt-driven-development` stress-tests a plan after you've drafted one. Interview-me is the part before all of those, where you ask one question at a time, with your best guess attached, until you can predict what the user is going to say before they say it.
## When to Use
Apply this skill when:
View the complete source on GitHubobservability-and-instrumentation
When your agent uses it
Instruments code so production behavior is visible and diagnosable. Use when adding logging, metrics, tracing, or alerting. Use when shipping any feature that runs in production and you need evidence it works. Use when production issues are reported but you can't tell what happened from the available data.
What it loads into context
Frontmatter
69 tokensAlways available to the agent
SKILL.md
3,160 tokensWhen the skill is activated
Reference documents
1,195 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Process
- Common Rationalizations
- Red Flags
- Verification
Files
../../references/observability-checklist.mddoc5,129 bytesSKILL.mdcore13,948 bytesSKILL.mdcore13,948 bytes
Read SKILL.md
# Observability and Instrumentation
## Overview
Code you can't observe is code you can't operate. Observability is the ability to answer "what is the system doing and why?" from the outside, using the telemetry the code emits. Instrumentation is not a post-launch add-on — it's written alongside the feature, the same way tests are. If a feature ships without telemetry, the first user-reported bug becomes archaeology instead of a query.
## When to Use
- Building any feature that will run in production
- Adding a new service, endpoint, background job, or external integration
- A production incident took too long to diagnose ("we couldn't tell what happened")
- Setting up or reviewing alerting rules
- Reviewing a PR that adds I/O, retries, queues, or cross-service calls
View the complete source on GitHubperformance-optimization
When your agent uses it
Optimizes application performance across frontend, backend, queries, and databases. Use when performance requirements exist, when you suspect performance regressions, when Core Web Vitals or load times need improvement, when N+1 query patterns need fixing, or when profiling reveals bottlenecks.
What it loads into context
Frontmatter
63 tokensAlways available to the agent
SKILL.md
3,834 tokensWhen the skill is activated
Reference documents
5,617 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Core Web Vitals Targets
- The Optimization Workflow
- See Also
- Common Rationalizations
- Red Flags
- Verification
Files
../../references/performance-checklist.mddoc13,292 bytesSKILL.mdcore16,783 bytesSKILL.mdcore16,783 bytesSKILL.mdcore16,783 bytesreferences/optimization-patterns.mddoc9,692 bytes
Read SKILL.md
# Performance Optimization
## Overview
Measure before optimizing. Performance work without measurement is guessing — and guessing leads to premature optimization that adds complexity without improving what matters. Profile first, identify the actual bottleneck, fix it, measure again. Optimize only what measurements prove matters.
## When to Use
- Performance requirements exist in the spec (load time budgets, response time SLAs)
- Users or monitoring report slow behavior
- Core Web Vitals scores are below thresholds
- You suspect a change introduced a regression
- Building features that handle large datasets or high traffic
View the complete source on GitHubplanning-and-task-breakdown
When your agent uses it
Breaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
What it loads into context
Frontmatter
60 tokensAlways available to the agent
SKILL.md
2,421 tokensWhen the skill is activated
Reference documents
827 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Planning Process
- Task Sizing Guidelines
- Output Files
- Plan Document Template
- Parallelization Opportunities
- Common Rationalizations
- Red Flags
- Verification
- See Also
Files
../../references/definition-of-done.mddoc3,798 bytesSKILL.mdcore10,564 bytes
Read SKILL.md
# Planning and Task Breakdown
## Overview
Decompose work into small, verifiable tasks with explicit acceptance criteria. Good task breakdown is the difference between an agent that completes work reliably and one that produces a tangled mess. Every task should be small enough to implement, test, and verify in a single focused session.
## When to Use
- You have a spec and need to break it into implementable units
- A task feels too large or vague to start
- Work needs to be parallelized across multiple agents or sessions
- You need to communicate scope to a human
- The implementation order isn't obvious
View the complete source on GitHubsecurity-and-hardening
When your agent uses it
Hardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions or session cookies, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved.
What it loads into context
Frontmatter
120 tokensAlways available to the agent
SKILL.md
3,866 tokensWhen the skill is activated
Reference documents
6,594 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Process: Threat Model First
- The Three-Tier Boundary System
- Hardening Controls
- Review Checklist
- Common Rationalizations
- Red Flags
- Verification
Files
../../references/security-checklist.mddoc14,503 bytesSKILL.mdcore17,578 bytesSKILL.mdcore17,578 bytesSKILL.mdcore17,578 bytesreferences/hardening-patterns.mddoc13,352 bytes
Read SKILL.md
# Security and Hardening
## Overview
Security-first development practices for web applications. Treat every external input as hostile, every secret as sacred, and every authorization check as mandatory. Security isn't a phase — it's a constraint on every line of code that touches user data, authentication, or external systems.
## When to Use
- Building anything that accepts user input
- Implementing authentication or authorization
- Storing or transmitting sensitive data
- Integrating with external APIs or services
- Adding file uploads, webhooks, or callbacks
- Handling payment or PII dataView the complete source on GitHubshipping-and-launch
When your agent uses it
Prepares production launches. Use when preparing to deploy to production, or when asking what needs to be in place before shipping. Use when you need a pre-launch checklist, when setting up monitoring, when planning a staged rollout, or when you need a rollback strategy.
What it loads into context
Frontmatter
61 tokensAlways available to the agent
SKILL.md
2,648 tokensWhen the skill is activated
Reference documents
8,822 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- The Pre-Launch Checklist
- Feature Flag Strategy
- Staged Rollout
- Monitoring and Observability
- Error Budget Release Gate
- Rollback Strategy
- See Also
- Common Rationalizations
- Red Flags
- Verification
Files
../../references/accessibility-checklist.mddoc5,332 bytes../../references/definition-of-done.mddoc3,798 bytes../../references/performance-checklist.mddoc13,292 bytes../../references/security-checklist.mddoc14,503 bytesSKILL.mdcore11,540 bytes
Read SKILL.md
# Shipping and Launch
## Overview
Ship with confidence. The goal is not just to deploy — it's to deploy safely, with monitoring in place, a rollback plan ready, and a clear understanding of what success looks like. Every launch should be reversible, observable, and incremental.
## When to Use
- Deploying a feature to production for the first time
- Releasing a significant change to users
- Migrating data or infrastructure
- Opening a beta or early access program
- Any deployment that carries risk (all of them)
View the complete source on GitHubsource-driven-development
When your agent uses it
Grounds every implementation decision in official documentation. Use when you want to verify an approach against the official docs before implementing it, or when you want authoritative, source-cited code free from outdated patterns. Use when building with any framework or library where correctness matters.
What it loads into context
Frontmatter
59 tokensAlways available to the agent
SKILL.md
2,102 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
- Overview
- When to Use
- The Process
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore10,104 bytesSKILL.mdcore10,104 bytesSKILL.mdcore10,104 bytesSKILL.mdcore10,104 bytes
Read SKILL.md
# Source-Driven Development
## Overview
Every framework-specific code decision must be backed by official documentation. Don't implement from memory — verify, cite, and let the user see your sources. Training data goes stale, APIs get deprecated, best practices evolve. This skill ensures the user gets code they can trust because every pattern traces back to an authoritative source they can check.
## When to Use
- The user wants code that follows current best practices for a given framework
- Building boilerplate, starter code, or patterns that will be copied across a project
- The user explicitly asks for documented, verified, or "correct" implementation
- Implementing features where the framework's recommended approach matters (forms, routing, data fetching, state management, auth)
- Reviewing or improving code that uses framework-specific patterns
- Any time you are about to write framework-specific code from memoryView the complete source on GitHubspec-driven-development
When your agent uses it
Creates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when drafting a PRD or requirements document with objectives and scope, or when requirements are unclear, ambiguous, or only exist as a vague idea. Use when a single requirement spans several independently testable capabilities and needs decomposing into a capability map of modules before specifying.
What it loads into context
Frontmatter
85 tokensAlways available to the agent
SKILL.md
2,794 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
- Overview
- When to Use
- The Gated Workflow
- Keeping the Spec Alive
- Common Rationalizations
- Red Flags
- Verification
Files
SKILL.mdcore13,099 bytesSKILL.mdcore13,099 bytesSKILL.mdcore13,099 bytesSKILL.mdcore13,099 bytesSKILL.mdcore13,099 bytes
Read SKILL.md
# Spec-Driven Development
## Overview
Write a structured specification before writing any code. The spec is the shared source of truth between you and the human engineer — it defines what we're building, why, and how we'll know it's done. Code without a spec is guessing.
## When to Use
- Starting a new project or feature
- Requirements are ambiguous or incomplete
- The change touches multiple files or modules
- You're about to make an architectural decision
- The task would take more than 30 minutes to implement
View the complete source on GitHubtest-driven-development
When your agent uses it
Drives development with tests using the red-green-refactor loop. Use when implementing any logic, fixing any bug, or changing any behavior. Use when you need to prove that code works, when a bug report arrives, or when you're about to modify existing functionality. Use when asked to add tests to a function, fix a bug in it or change its behavior, even when the code is pasted inline and the request does not mention tests.
What it loads into context
Frontmatter
95 tokensAlways available to the agent
SKILL.md
3,793 tokensWhen the skill is activated
Reference documents
1,853 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- When to Use
- Discover the Stack First
- The TDD Cycle
- The Prove-It Pattern (Bug Fixes)
- The Test Pyramid
- Writing Good Tests
- Test Anti-Patterns to Avoid
- Browser Testing with DevTools
- When to Use Subagents for Testing
- See Also
- Common Rationalizations
- Red Flags
- Verification
Files
../../references/testing-patterns.mddoc7,543 bytesSKILL.mdcore16,845 bytesSKILL.mdcore16,845 bytes
Read SKILL.md
# Test-Driven Development
## Overview
Write a failing test before writing the code that makes it pass. For bug fixes, reproduce the bug with a test before attempting a fix. Tests are proof — "seems right" is not done. A codebase with good tests is an AI agent's superpower; a codebase without tests is a liability.
## When to Use
- Implementing any new logic or behavior
- Fixing any bug (the Prove-It Pattern)
- Modifying existing functionality
- Adding edge case handling
- Any change that could break existing behavior
View the complete source on GitHubusing-agent-skills
When your agent uses it
Discovers and invokes agent skills. Use when starting a session, or when you need to decide which skill or workflow applies to the piece of work at hand. This is the meta-skill that governs how all other skills are discovered and invoked.
What it loads into context
Frontmatter
58 tokensAlways available to the agent
SKILL.md
2,208 tokensWhen the skill is activated
Reference documents
827 tokensLoaded on request
Token counts are estimates. Scripts run separately; they are not counted as reference context.
The playbook
- Overview
- Skill Discovery
- Core Operating Behaviors
- Failure Modes to Avoid
- Skill Rules
- Lifecycle Sequence
- Quick Reference
Files
../../references/definition-of-done.mddoc3,798 bytesSKILL.mdcore10,446 bytes
Read SKILL.md
# Using Agent Skills
## Overview
Agent Skills is a collection of engineering workflow skills organized by development phase. Each skill encodes a specific process that senior engineers follow. This meta-skill helps you discover and apply the right skill for your current task.
## Skill Discovery
When a task arrives, identify the development phase and apply the corresponding skill:
```
Task arrives
│
├── Don't know what you want yet? ──────→ interview-meView the complete source on GitHubSkills included
- api-and-interface-design
- browser-testing-with-devtools
- ci-cd-and-automation
- code-review-and-quality
- code-simplification
- constraint-driven-development
- context-engineering
- debugging-and-error-recovery
- deprecation-and-migration
- documentation-and-adrs
- doubt-driven-development
- frontend-ui-engineering
- git-workflow-and-versioning
- idea-refine
- incremental-implementation
- interview-me
- observability-and-instrumentation
- performance-optimization
- planning-and-task-breakdown
- security-and-hardening
- shipping-and-launch
- source-driven-development
- spec-driven-development
- test-driven-development
- using-agent-skills
Repository facts
- License
- MIT
- Created
- Feb 15, 2026
- Last pushed
- Nov 1, 2026
- Forks
- 11,865
- Open issues
- 56
- Project activity
- Active
Rank over the last 12 weeks
Now #12 · best #12 · same as 30 days ago
- #13 on Aug 8
- #12 from Aug 9 to Aug 16
- #13 from Aug 17 to Sep 18
- #12 from Sep 19 to Oct 24
- #13 on Oct 25
- #12 since Oct 28
2 earlier periods
- #14 on Aug 2
- #14 on Aug 7
Before you install
Network or broad shellAutomated signals, not a guarantee
Checked Nov 3, 2026
Not fully analyzed: some files were too long, unreadable or missing. This never lowers the level.
Show 40 notes
.claude/commands/webperf.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedcommands/webperf.toml:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/browser-testing-with-devtools/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/ci-cd-and-automation/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude/commands/webperf.md:1Plugin-wide analysis incomplete; see repository notesskills/code-simplification/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/constraint-driven-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/context-engineering/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/context-engineering/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/debugging-and-error-recovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/debugging-and-error-recovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/debugging-and-error-recovery/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude/commands/webperf.md:1Plugin-wide analysis incomplete; see repository notesskills/documentation-and-adrs/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/doubt-driven-development/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed.claude/commands/webperf.md:1Plugin-wide analysis incomplete; see repository notesskills/git-workflow-and-versioning/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/git-workflow-and-versioning/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/git-workflow-and-versioning/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzedskills/git-workflow-and-versioning/SKILL.md:1Analysis incomplete: Referenced executable target unavailable; not analyzed
- No broad tool permissions
- No dangerous shell commands
- 66 network referencesin 10 files: references/security-checklist.md:122 skills/security-and-hardening/references/hardening-patterns.md:105 references/performance-checklist.md:189 and 7 more
- No hidden or obfuscated text
- No instruction overrides
- 4 executable scriptsin 2 files: skills/constraint-driven-development/scripts/quality-gate.mjs:1 skills/idea-refine/scripts/idea-refine.sh:1
- 27 references to secretsin 8 files: skills/security-and-hardening/references/hardening-patterns.md:36 references/security-checklist.md:32 skills/browser-testing-with-devtools/SKILL.md:64 and 5 more
- No requests to vote in Hot
Show all 97 signals by file
.claude-plugin/marketplace.json
- Network accessline 1
{ "$schema": "https://json.schemastore.org/claude-code-marketplace.json", - Network accessline 2
"$schema": "https://json.schemastore.org/claude-code-marketplace.json", - Network accessline 5
"owner": { "name": "Addy Osmani", "url": "https://github.com/addyosmani" - Network accessline 6
"name": "Addy Osmani", "url": "https://github.com/addyosmani" }, - Network accessline 7
"url": "https://github.com/addyosmani" - Network accessline 16
}, "description": "Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.", "homepage": "https://github.com/addyosmani/agent-skills", - Network accessline 17
"description": "Production-grade engineering skills covering every phase of software development: spec, plan, build, verify, review, and ship.", "homepage": "https://github.com/addyosmani/agent-skills", "license": "MIT", - Network accessline 18
"homepage": "https://github.com/addyosmani/agent-skills",
.claude-plugin/plugin.json
- Network accessline 6
"name": "Addy Osmani" }, "homepage": "https://github.com/addyosmani/agent-skills", - Network accessline 7
}, "homepage": "https://github.com/addyosmani/agent-skills", "repository": "https://github.com/addyosmani/agent-skills", - Network accessline 8
"homepage": "https://github.com/addyosmani/agent-skills", - Network accessline 9
"repository": "https://github.com/addyosmani/agent-skills",
.claude/commands/webperf.md
- Access to secretsline 13
[Credential-related source omitted]
commands/webperf.toml
- Access to secretsline 11
[Credential-related source omitted]
references/accessibility-checklist.md
- Network accessline 126
# Automated audit npx --package=@axe-core/cli axe http://localhost:3000 - Network accessline 126
# Automated audit npx --package=@axe-core/cli axe http://localhost:3000 - Network accessline 127
npx --package=@axe-core/cli axe http://localhost:3000 - Network accessline 127
npx --package=@axe-core/cli axe http://localhost:3000
references/performance-checklist.md
- Network accessline 189
1. **Field data first** — check [CrUX Vis](https://developer.chrome.com/docs/crux/vis) or your RUM tool for real-user INP before optimising - Network accessline 189
1. **Field data first** — check [CrUX Vis](https://developer.chrome.com/docs/crux/vis) or your RUM tool for real-user INP before optimising - Network accessline 189
1. **Field data first** — check [CrUX Vis](https://developer.chrome.com/docs/crux/vis) or your RUM tool for real-user INP before optimising - Network accessline 194
# Lighthouse CLI npx lighthouse http://localhost:3000 --output json --output-path ./report.json - Network accessline 194
# Lighthouse CLI npx lighthouse http://localhost:3000 --output json --output-path ./report.json - Network accessline 194
# Lighthouse CLI npx lighthouse http://localhost:3000 --output json --output-path ./report.json - Network accessline 195
npx lighthouse http://localhost:3000 --output json --output-path ./report.json - Network accessline 195
npx lighthouse http://localhost:3000 --output json --output-path ./report.json - Network accessline 195
npx lighthouse http://localhost:3000 --output json --output-path ./report.json
references/security-checklist.md
- Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Access to secretsline 32
[Credential-related source omitted] - Network accessline 122
// Restrictive (recommended) cors({ origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], - Network accessline 122
// Restrictive (recommended) cors({ origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], - Network accessline 122
// Restrictive (recommended) cors({ origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], - Network accessline 123
cors({ origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], credentials: true, - Network accessline 123
cors({ origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], credentials: true, - Network accessline 123
cors({ origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], credentials: true, - Network accessline 124
origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], - Network accessline 124
origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], - Network accessline 124
origin: ['https://yourdomain.com', 'https://app.yourdomain.com'], - Network accessline 182
Authoritative checks: [npm install-scripts](https://docs.npmjs.com/cli/v11/commands/npm-install-scripts/), [install policy](https://docs.npmjs.com/cli/v11/commands/npm-install/), and [CLI releases](https://github.com/npm/cli/releases); [pnp - Network accessline 182
Authoritative checks: [npm install-scripts](https://docs.npmjs.com/cli/v11/commands/npm-install-scripts/), [install policy](https://docs.npmjs.com/cli/v11/commands/npm-install/), and [CLI releases](https://github.com/npm/cli/releases); [pnp - Network accessline 182
Authoritative checks: [npm install-scripts](https://docs.npmjs.com/cli/v11/commands/npm-install-scripts/), [install policy](https://docs.npmjs.com/cli/v11/commands/npm-install/), and [CLI releases](https://github.com/npm/cli/releases); [pnp - Network accessline 235
For apps with LLM features. See the [OWASP GenAI Security Project](https://genai.owasp.org/llm-top-10/). - Network accessline 235
For apps with LLM features. See the [OWASP GenAI Security Project](https://genai.owasp.org/llm-top-10/). - Network accessline 235
For apps with LLM features. See the [OWASP GenAI Security Project](https://genai.owasp.org/llm-top-10/).
skills/browser-testing-with-devtools/SKILL.md
- Access to secretsline 64
[Credential-related source omitted] - Access to secretsline 64
[Credential-related source omitted] - Network accessline 193
### Setup 1. Navigate to http://localhost:3000/tasks - Network accessline 193
### Setup 1. Navigate to http://localhost:3000/tasks - Network accessline 194
1. Navigate to http://localhost:3000/tasks - Network accessline 194
1. Navigate to http://localhost:3000/tasks
skills/ci-cd-and-automation/SKILL.md
skills/code-simplification/SKILL.md
- Network accessline 8
> Inspired by the [Claude Code Simplifier plugin](https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md). Adapted here as a model-agnostic, process-driven skill for any AI coding a - Network accessline 8
> Inspired by the [Claude Code Simplifier plugin](https://github.com/anthropics/claude-plugins-official/blob/main/plugins/code-simplifier/agents/code-simplifier.md). Adapted here as a model-agnostic, process-driven skill for any AI coding a
skills/constraint-driven-development/scripts/quality-gate.mjs
skills/context-engineering/SKILL.md
skills/git-workflow-and-versioning/SKILL.md
skills/idea-refine/scripts/idea-refine.sh
skills/security-and-hardening/SKILL.md
- Network accessline 156
Calling an LLM — chatbots, summarizers, agents, RAG — adds a new attack surface; map it to the [OWASP Top 10 for LLM Applications (2025)](https://genai.owasp.org/llm-top-10/): - Network accessline 156
Calling an LLM — chatbots, summarizers, agents, RAG — adds a new attack surface; map it to the [OWASP Top 10 for LLM Applications (2025)](https://genai.owasp.org/llm-top-10/):
skills/security-and-hardening/references/hardening-patterns.md
- Access to secretsline 36
[Credential-related source omitted] - Access to secretsline 36
[Credential-related source omitted] - Network accessline 105
// CORS — restrict to known origins app.use(cors({ origin: process.env.ALLOWED_ORIGINS?.split(',') || 'http://localhost:3000', - Network accessline 105
// CORS — restrict to known origins app.use(cors({ origin: process.env.ALLOWED_ORIGINS?.split(',') || 'http://localhost:3000', - Network accessline 106
app.use(cors({ origin: process.env.ALLOWED_ORIGINS?.split(',') || 'http://localhost:3000', credentials: true, - Network accessline 106
app.use(cors({ origin: process.env.ALLOWED_ORIGINS?.split(',') || 'http://localhost:3000', credentials: true, - Network accessline 107
origin: process.env.ALLOWED_ORIGINS?.split(',') || 'http://localhost:3000', - Network accessline 107
origin: process.env.ALLOWED_ORIGINS?.split(',') || 'http://localhost:3000', - Access to secretsline 122
[Credential-related source omitted] - Access to secretsline 122
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Access to secretsline 123
[Credential-related source omitted] - Network accessline 131
// BAD: fetch whatever the user gives you await fetch(req.body.webhookUrl); - Network accessline 131
// BAD: fetch whatever the user gives you await fetch(req.body.webhookUrl); - Network accessline 132
await fetch(req.body.webhookUrl); - Network accessline 132
await fetch(req.body.webhookUrl); - Network accessline 152
await fetch(await assertSafeUrl(req.body.webhookUrl), { redirect: 'error' }); - Network accessline 152
await fetch(await assertSafeUrl(req.body.webhookUrl), { redirect: 'error' }); - Access to secretsline 281
[Credential-related source omitted] - Access to secretsline 281
[Credential-related source omitted] - Access to secretsline 283
[Credential-related source omitted] - Access to secretsline 283
[Credential-related source omitted] - Access to secretsline 287
[Credential-related source omitted] - Access to secretsline 287
[Credential-related source omitted] - Access to secretsline 299
[Credential-related source omitted] - Access to secretsline 299
[Credential-related source omitted]
skills/source-driven-development/SKILL.md
- Network accessline 148
// React 19 form handling with useActionState // Source: https://react.dev/reference/react/useActionState#usage - Network accessline 148
// React 19 form handling with useActionState // Source: https://react.dev/reference/react/useActionState#usage - Network accessline 149
// Source: https://react.dev/reference/react/useActionState#usage - Network accessline 149
// Source: https://react.dev/reference/react/useActionState#usage - Network accessline 160
Source: https://react.dev/blog/2024/12/05/react-19#actions - Network accessline 160
Source: https://react.dev/blog/2024/12/05/react-19#actions
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.
Signal confidence: 84 facts
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored value.claude/commands/webperf.md:13Low confidence
- Network access in code of documentationreferences/accessibility-checklist.md:126Low confidence
- Network access in code of documentationreferences/accessibility-checklist.md:126Low confidence
- Network access in code of documentationreferences/accessibility-checklist.md:127Low confidence
- Network access in code of documentationreferences/accessibility-checklist.md:127Low confidence
- Network access in prose of documentationreferences/performance-checklist.md:189Low confidence
- Network access in prose of documentationreferences/performance-checklist.md:189Low confidence
- Network access in prose of documentationreferences/performance-checklist.md:189Low confidence
- Network access in code of documentationreferences/performance-checklist.md:194Low confidence
- Network access in code of documentationreferences/performance-checklist.md:194Low confidence
- Network access in code of documentationreferences/performance-checklist.md:194Low confidence
- Network access in code of documentationreferences/performance-checklist.md:195Low confidence
- Network access in code of documentationreferences/performance-checklist.md:195Low confidence
- Network access in code of documentationreferences/performance-checklist.md:195Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valuereferences/security-checklist.md:32Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valuereferences/security-checklist.md:32Low confidence
- Access to secrets in prose of documentation: a variable, placeholder or call, not a stored valuereferences/security-checklist.md:32Low confidence
- Network access in code of documentationreferences/security-checklist.md:122Low confidence
- Network access in code of documentationreferences/security-checklist.md:122Low confidence
- Network access in code of documentationreferences/security-checklist.md:122Low confidence
- Network access in code of documentationreferences/security-checklist.md:123Low confidence
- Network access in code of documentationreferences/security-checklist.md:123Low confidence
- Network access in code of documentationreferences/security-checklist.md:123Low confidence
- Network access in code of documentationreferences/security-checklist.md:124Low confidence
- Network access in code of documentationreferences/security-checklist.md:124Low confidence
- Network access in code of documentationreferences/security-checklist.md:124Low confidence
- Network access in prose of documentationreferences/security-checklist.md:182Low confidence
- Network access in prose of documentationreferences/security-checklist.md:182Low confidence
- Network access in prose of documentationreferences/security-checklist.md:182Low confidence
- Network access in prose of documentationreferences/security-checklist.md:235Low confidence
- Network access in prose of documentationreferences/security-checklist.md:235Low confidence
- Network access in prose of documentationreferences/security-checklist.md:235Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valueskills/browser-testing-with-devtools/SKILL.md:64Low confidence
- Access to secrets in prose of the SKILL.md: a variable, placeholder or call, not a stored valuebrowser-testing-with-devtools/SKILL.md:64Low confidence
- Network access in code of the SKILL.mdskills/browser-testing-with-devtools/SKILL.md:193High confidence
- Network access in code of the SKILL.mdbrowser-testing-with-devtools/SKILL.md:193High confidence
- Network access in code of the SKILL.mdskills/browser-testing-with-devtools/SKILL.md:194High confidence
- Network access in code of the SKILL.mdbrowser-testing-with-devtools/SKILL.md:194High confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueskills/ci-cd-and-automation/SKILL.md:278Low confidence
- Access to secrets in code of the SKILL.md: a variable, placeholder or call, not a stored valueci-cd-and-automation/SKILL.md:278Low confidence
- Network access in prose of the SKILL.mdskills/code-simplification/SKILL.md:8Low confidence
- Network access in prose of the SKILL.mdcode-simplification/SKILL.md:8Low confidence
- Executable script in code of a file that runsskills/constraint-driven-development/scripts/quality-gate.mjs:1High confidence
- Executable script in code of a file that runsconstraint-driven-development/scripts/quality-gate.mjs:1High confidence
- Access to secrets in code of the SKILL.mdskills/context-engineering/SKILL.md:65High confidence
- Access to secrets in code of the SKILL.mdcontext-engineering/SKILL.md:65High confidence
- Access to secrets in code of the SKILL.mdskills/git-workflow-and-versioning/SKILL.md:220High confidence
- Access to secrets in code of the SKILL.mdgit-workflow-and-versioning/SKILL.md:220High confidence
- Executable script in code of a file that runsskills/idea-refine/scripts/idea-refine.sh:1High confidence
- Executable script in code of a file that runsidea-refine/scripts/idea-refine.sh:1High confidence
and 34 more
Works with
| Agent | Status | Evidence | Install to |
|---|---|---|---|
| Claude Code | Native | Manifest .claude-plugin/marketplace.json | .claude/skills/<skill-name>/ |
| Codex | Native | Manifest AGENTS.md | .agents/skills/<skill-name>/ |
| Cursor | Compatible | Standard SKILL.md skills/api-and-interface-design/SKILL.md | .cursor/skills/<skill-name>/ |
| Gemini CLI | Native | Path .gemini/commands/build.toml | .gemini/skills/<skill-name>/ |
| GitHub Copilot | Compatible | Standard SKILL.md skills/api-and-interface-design/SKILL.md | .github/skills/<skill-name>/ |
| OpenCode | Native | Path .opencode/skills | .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/addyosmani-agent-skills/)