zernie
UserLike Lighthouse for your agent harness - verify your CLAUDE.md/AGENTS.md, skills & hooks are real, then test and measure they actually work. Claude Code + Codex.
Categories
Indexed Skills (29)
edit-spec
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 whenever you need to change a CLAUDE.md/AGENTS.md that carries a vigiles hash (edit the spec, never the artifact), including adding a new enforce()/check()/guidance() rule.
debug-my-harness
Diagnose why an agent harness misbehaved by reading the local flight-recorder ledger (.vigiles/runs.jsonl) — which skills fired or got hijacked, which hooks blocked or wrongly allowed, which subagent tool-contract violations happened, and how a skill's trigger rate moved. Use when asked why a skill stopped firing, why a hook didn't block, why the wrong skill ran, or to debug/investigate what the harness actually did. NOT for writing new rules (use strengthen) or editing the spec (use edit-spec).
strengthen
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, Clippy, Pylint, RuboCop, Stylelint) that back them. Use when asked to strengthen, harden, or make vigiles rules enforceable; NOT for general linting or fixing lint errors.
test-harness
Install vigiles and test a Claude Code harness — hooks, skills, agents, settings, CLAUDE.md — by picking the right tier (unit / deterministic / eval) and writing a test that passes. Use to check that a hook fires or blocks, that a skill triggers, that injected context lands; or to observe a run — which tools it called, whether it stayed inside its declared allowed-tools, what files and side effects it produced, how to intercept a call without executing it.
add-a-linter
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 test enforcing docs + site parity so no site is forgotten
audience-check
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
enforce-rules-format
Validate that all rules have proper enforcement classification (enforce/check/guidance)
pr-to-lint-rule
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 prove sound
verify-docs-findable
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 how fast they reach the answer, whether they hit dead-ends, whether they fall back to source code, and whether they cite docs that contradict each other. Use after a doc reorg, when docs "feel scattered," or when the same confusion keeps recurring. Surfaces findability gaps (a corpus can be COMPLETE — every doc indexed — yet not FINDABLE) plus a prioritized fix list. Works on any repo's docs, not just this one.
adopt-spec
Adopt a typed .spec.ts for an existing hand-written CLAUDE.md — start from the file you already have, non-destructively
linter-docs
Deep linter reference for authoring or debugging a vigiles enforce() rule — plugin tables, AST selectors, type-aware rules, auto-fix, and edge cases for ESLint, Ruff, Pylint, RuboCop, Stylelint, and Clippy. Use when you need the exact rule name or config for a specific linter, not for running a linter. (JVM/Go linters — detekt, ktlint, Checkstyle, golangci-lint — and Cedar have no deep-dive file yet; their reference lives in docs/linter-support.md.)
landing-site
The purpose, UX flow, and modern-minimalist design bar for the vigiles.sh landing site (site/). Use whenever designing, editing, adding to, or reviewing any site/ component, hero, section, or marketing copy — read it BEFORE touching site/, and hold every change against it. Not for docs/ or the app itself.
dogfood-cli
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 regression test, commit per theme. Use when asked to dogfood vigiles, find/fix bugs across the CLI the source-traced way, or fan out agents to audit the tool on itself.
code-quality
Improve the quality and type-safety of TypeScript/JavaScript being written or refactored — parse-don't-validate, make-illegal-states-irrepresentable, exhaustive matching, pure-function/IO separation, and public-API hygiene. Use when asked to refactor, clean up, improve, harden, or review the design/quality of code or an API. NOT for hunting bugs (that's /code-review) and NOT for vigiles's own spec/lint rules.
deep-research
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 agents — anything where many findings must be gathered and then NOT lost. Enforces durable, detail-preserving research (write full findings to disk; keep a full appendix beside the synthesis).
generate-logo
Generate or iterate on the vigiles logo using ImageRouter API
review-docs
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 newcomer, power user, plugin/skill author, skeptical senior engineer, non-running decision-maker — each scoring it x/5 and naming concrete, line-level fixes. Use when asked to review, critique, grade, or "get to N/5" the README or any front-door doc, or to check how a doc reads for real users. Not for code review (use /code-review for that).
screenshot
Render a local web page / built site and capture full-page screenshots (desktop + mobile) using the pre-installed Chromium. Use when asked to screenshot, render, or "see how it looks" for the vigiles landing site (site/), the audit report (report/), or any local HTML/dev server. Handles the scroll-reveal gotcha (below-the-fold cards captured blank) automatically.
caveman
Ultra-compressed communication mode. Cuts token usage ~75% by speaking like caveman while keeping full technical accuracy. Supports intensity levels: lite, full (default), ultra, wenyan-lite, wenyan-full, wenyan-ultra. Use when user says "caveman mode", "talk like caveman", "use caveman", "less tokens", "be brief", or invokes /caveman. Also auto-triggers when token efficiency is requested.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes
test-driven-development
Use when implementing any feature or bugfix, before writing implementation code
screen-reader-testing
Test web applications with screen readers including VoiceOver, NVDA, and JAWS. Use when validating screen reader compatibility, debugging accessibility issues, or ensuring assistive technology support.
wcag-audit-patterns
Conduct WCAG 2.2 accessibility audits with automated testing, manual verification, and remediation guidance. Use when auditing websites for accessibility, fixing WCAG violations, or implementing accessible design patterns.
ask
Process-first advisor routing for Claude, Codex, or Gemini via `omc ask`, with artifact capture and no raw CLI assembly
verify
Verify that a change really works before you claim completion
add-cart-discount
Add per-item discount support to the cart total
implement-parse-list
Implement the parseList string utility
switch-name-format
Switch name rendering to "last, first"
implement-is-odd
Implement isOdd following test-driven development
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.