canon-skills

Exports any flat canon skill as a paste-ready prompt, or refines an existing prompt using efficiency.md standards. Use when running a skill in claude.ai, a system prompt, or another environment that doesn't load SKILL.md natively. Invoke as skill-export <skill-name> or skill-export <skill-name> "<prompt>". Rejects skills with sub-skills.

Manages the sprint workflow for focused changes. Use when asked to add, fix, update, implement, debug, or build — see the Workflow tiers section for what's out of scope.

Internal close-pipeline invoked by sprint complete — quality checks, code review, cleanup. Not for direct use; a normal/high-risk sprint's own "sprint complete" step calls this automatically.

Converts a title or heading into a URL-safe slug (lowercase, hyphen-separated). Use when generating a filename, anchor link, or URL path segment from a title.

Generates Marp slide decks from canon knowledge. Use when asked to create slides, build a presentation, or generate a deck on a canon topic (context management, evaluator pattern, or skill authoring). Renders to HTML and PPTX for browser viewing and SharePoint/PowerPoint distribution.

Validates agent-generated reports and summaries before delivery. Catches generator-evaluator collapse — where the AI summarizes data without checking if the summary is true. Run before delivering any report, status update, or data summary.

Reviews open PRs on sunitghub/canon-skills — fetches diffs, presents findings, updates PRs/canon-skills-pr-review.md, creates tickets for Fix=Y PRs, and posts approved comments. Use when the user asks to review canon-skills PRs or check what's open on canon-skills.

Audit user-facing docs for overstated claims, missing prerequisites, absolutes, scope inflation, and stale commands.

Runs a fresh-context, 4-way parallel audit of a canon workflow's own skill/reference docs against themselves — pipeline gates, adversarial review, cross-doc consistency, stale-reference sweep. Use when asked to deep-scan, audit, or health-check the sprint/wrapup workflow docs (or another skill's own protocol files) for internal contradictions, staleness, or drift — not for auditing a whole repo's product code (use repo-audit for that).

Maintains a repo-local HANDOFF.md as working memory for session continuity, so a new agent session can resume without re-explaining prior work. Use when work stops with uncommitted changes, a non-obvious discovery is made mid-task, a new session needs to pick up where the last one left off, or the user asks to save state/progress for later.

Converts a title or heading into a URL-safe slug (lowercase, hyphen-separated). Use when generating a filename, anchor link, or URL path segment from a title.

Converts a title or heading into a URL-safe slug (lowercase, hyphen-separated). Use when generating a filename, anchor link, or URL path segment from a title.

Converts a title or heading into a URL-safe slug (lowercase, hyphen-separated). Use when generating a filename, anchor link, or URL path segment from a title.

Audit a repo across four dimensions — uniqueness and selling point, philosophy-to-implementation coherence, setup and doc effectiveness, and codebase quality (DRY, KISS, SRP, composition). Invoke when asked to review, assess, or health-check a repo.

Helps the user with things.

Fetches a URL and summarizes the content. Use when asked to retrieve a webpage or document and produce a summary of it.

Runs execution evals for a named skill against test cases in evals/evals.json. Use when you want to verify a skill produces correct output for known prompts, check skill quality after edits, or confirm a new skill works before registering it.

Audits always-on context load for bloat, redundancy, and quality. Use when context feels heavy or periodically to keep the always-on budget lean.

Records non-obvious discoveries, constraints, and gotchas to HANDOFF.md. Use when something surprising is found mid-sprint.