Audit a website's SEO health (on-page, technical, structured data, social, performance) from a live URL or from the project's source code, producing a prioritized report. Use when the user asks to audit/check/improve SEO, search ranking, meta tags, structured data, sitemap, or robots.txt, or shares a homepage URL to…
Failure-mode-driven reliability engineering — enumerate how it breaks, give every mode a verdict, prove every handler with a reproducing test. Use when the user says "flaky", "harden this before launch", "what if this fails", "error handling", "timeout", "retry", "idempotency", or "race condition"; when an incident or…
Launch, positioning, and promotion — making finished work land with the audience that should care. Use when the user says "launch", "announce", "release notes", "changelog", "blog post", "tweet thread", "X thread", "Show HN", "Hacker News post", "how do I promote this", "who would care about this", or "positioning"…
Skill forging — distilling a team's recurring, hard-won practice into a new installable SKILL.md that meets the nen contract. Use when the user says "write a skill", "create a skill for", "turn this workflow into a skill", "codify our process", or "SKILL.md"; when someone says "we keep solving this the same way" or…
Project handover — write timestamped handoff docs under .handoff/ with HANDOFF.md as symlink to latest. Handles project, submodule, task, and archive handoffs.
Full GitLab development loop — from issue to confirmed-resolved. Covers write-issue, analyze-issue, fix-issue, review-code, create-mr, summarize-issue, triage-issue, and post-merge verification.
Use when replying to comments on a GitLab issue, or when an issue has comments that might tag you or be waiting on your reply as assignee — figures out which comments genuinely need a response, drafts each reply grounded in the codebase, and posts after you confirm.
Write a committed handoff checkpoint so a fresh session can resume with zero loss. Use when crossing the 40% context line, on every stage transition, and at session end. Writes .trace/checkpoints/ - .md while the agent is still sharp.
The forward code-quality constraint (Clean Code). Use while writing code in the implement stage and as a review lens in evaluate. Intention-revealing names, small single-responsibility functions, no duplication, comments that explain why not what.
This project runs on harness-mini. For non-trivial work — a feature, a multi-step or ambiguous change, anything cross-cutting — route it through the stage-viewer skill first and prefer harness-mini's lifecycle, skills, and sub-agents (read .claude/skills/ /SKILL.md) over ad-hoc tools or other installed plugins. When a…
Source-faithful summary rules for text, video transcripts, audio transcripts, interviews, lectures, demos, and meetings.
★not rated 2 3mo agoA0 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: