@skills · Owner

Agent skills by zernie

58 skills indexed from github.com/zernie. Reference any of them in AdaL, Claude Code, Cursor or any coding agent — nothing to install.

• .claude · Collection · 13 stars
• add-a-linter · Skill · 13 stars

  Add a new linter to vigiles's cross-referencing engine as one cohesive, type-enforced unit — a LinterAdapter in the LINTERS registry, with the conformance

• add-cart-discount · Skill · 13 stars

  Add per-item discount support to the cart total

• adopt-spec · Skill · 13 stars

  Adopt a typed .spec.ts for an existing hand-written CLAUDE.md — start from the file you already have, non-destructively

• ask · Skill · 13 stars

  Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly

• audience-check · Skill · 13 stars

  Read the README (or any front-door doc) through the eyes of several distinct audience personas and report what each would think, miss, or bounce on

• audit-feedback-loop · Skill · 13 stars

  Scan the current repo and score its feedback loop maturity for AI-assisted development

• bench · Collection · 13 stars
• caveman · Skill · 13 stars

  Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite,

• caveman · Skill · 13 stars

  Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite,

• caveman-plugin · Collection · 13 stars
• code-quality · Skill · 13 stars

  Improve the quality and type-safety of TypeScript/JavaScript being written or refactored — parse-don't-validate, make-illegal-states-irrepresentable, exhau

• debug-my-harness · Skill · 13 stars

  Diagnose why an agent harness misbehaved by reading the local flight-recorder ledger (.vigiles/runs.jsonl) — which skills fired or got hijacked, which hook

• deep-research · Skill · 13 stars

  Use when the user asks to research a topic in depth, map a competitive/market landscape, run a multi-source investigation, or "fan out" parallel research a

• dogfood · Collection · 13 stars
• dogfood-cli · Skill · 13 stars

  Hunt for real bugs in the vigiles CLI/codebase with a parallel expert fan-out, then FIX them directly — source-trace each defect to file:line, add a regres

• ecosystem · Collection · 13 stars
• edit-spec · Skill · 13 stars

  Edit a vigiles .spec.ts to change a compiled instruction file (CLAUDE.md / AGENTS.md) — add, modify, or remove a rule, section, command, or key file. Use w

• enforce-rules-format · Skill · 13 stars

  Validate that all rules have proper enforcement classification (enforce/check/guidance)

• generate-logo · Skill · 13 stars

  Generate or iterate on the vigiles logo using ImageRouter API

• implement-is-odd · Skill · 13 stars

  Implement isOdd following test-driven development

• implement-parse-list · Skill · 13 stars

  Implement the parseList string utility

• landing-site · Skill · 13 stars

  The purpose, UX flow, and modern-minimalist design bar for the vigiles.sh landing site (site/). Use whenever designing, editing, adding to, or reviewing an

• linter-docs · Skill · 13 stars

  Deep linter reference for authoring or debugging a vigiles enforce() rule — plugin tables, AST selectors, type-aware rules, auto-fix, and edge cases for ES

• oh-my-claudecode@deee3a4 · Collection · 13 stars
• pr-to-lint-rule · Skill · 13 stars

  Synthesize a recurring code-review rule into a custom lint rule — gated by an independent soundness test that abstains rather than ship a checker it can't

• pr-to-lint-rule · Skill · 13 stars

  Convert a recurring PR review comment into an automated lint rule with tests and CLAUDE.md annotation

• review-docs · Skill · 13 stars

  Review the README or a documentation page from several real reader points of view at once. Fans out one parallel reviewer per audience — Claude Code newcom

• screen-reader-testing · Skill · 13 stars

  Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility iss

• screenshot · Skill · 13 stars

  Render a local web page / built site and capture full-page screenshots (desktop + mobile) using the pre-installed Chromium. Use when asked to screenshot, r

• skills · Collection · 13 stars
• skills · Collection · 13 stars
• skills · Collection · 13 stars
• skills · Collection · 13 stars
• skills · Collection · 13 stars
• skills · Collection · 13 stars
• skills · Collection · 13 stars
• strengthen · Skill · 13 stars

  Upgrade a vigiles spec's guidance() rules to enforce() — scan the guidance rules in a CLAUDE.md/AGENTS.md spec and find existing linter rules (ESLint, Ruff

• superpowers@6fd4507 · Collection · 13 stars
• switch-name-format · Skill · 13 stars

  Switch name rendering to "last, first

• systematic-debugging · Skill · 13 stars

  Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

• tasks · Collection · 13 stars
• tdd · Collection · 13 stars
• test · Collection · 13 stars
• test-driven-development · Skill · 13 stars

  Use when implementing any feature or bugfix, before writing implementation code

• test-harness · Skill · 13 stars

  Install vigiles and test a Claude Code harness — hooks, skills, agents, settings, CLAUDE.md — by picking the right tier (unit / deterministic / eval) and w

• verify · Skill · 13 stars

  Verify that a change really works before you claim completion

• verify-docs-findable · Skill · 13 stars

  Audit whether a repo's docs actually ANSWER the questions a reader has — by spawning fresh, cheap (Haiku) agents that cold-read ONLY the docs and measuring

• vigiles · Collection · 13 stars
• wcag-audit-patterns · Skill · 13 stars

  Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility,

• wshobson-accessibility@cf6059d · Collection · 13 stars
• .claude · Collection
• claude-octopus@5a9cab8 · Collection
• flow-define · Skill

  Multi-AI requirements scoping using available external providers (Double Diamond Define phase)

• flow-define · Skill

  Multi-AI requirements scoping using available external providers (Double Diamond Define phase)

• ship-a-feature · Skill

  Ship a NEW capability to vigiles so it actually reaches a user — a new export, public function, subpath, CLI flag, or hook-vocabulary word. Use when about

• skills · Collection
• skills · Collection

Browse the @skills marketplace