All categories
Tools & Automation
CLI tools, utilities, converters, workflow automation, and productivity helpers
- 46,779
- 1,950
Security grades appear on each card once the skill has been scanned. Newly imported skills may briefly show without a grade until the backfill job runs.
Open in full browserBrowse tools & automation skills
Showing 1,969–1,992 of 46,779 skills
- ReviewerReviews pull requests for style and correctness issues.Votes: 0GitHub stars: 2
- Shared SkillA skill in the shared .claude/skills location Copilot also reads.Votes: 0GitHub stars: 2
- Xjust a skillVotes: 0GitHub stars: 2
- BetaA project-local skill for formatting.Votes: 0GitHub stars: 2
- AlphaA global skill used across projects.Votes: 0GitHub stars: 2
- Broken SkillNo frontmatter here, just a heading below.Votes: 0GitHub stars: 2
- WrappedCreates a shareable usage summary card from the user's local coding agent session logs (sessions, tokens, estimated cost, streaks, busiest hours). Use when the user asks for their Wrapped, a usage recap or stats card, how much they used Claude Code, or runs /setup-doctor:wrapped.Votes: 0GitHub stars: 2
- DoctorAudits the user's AI coding agent setup and returns a 0 to 100 score with fixes. Use when the user asks to check, audit, score, lint or improve their CLAUDE.md, skills, MCP servers, plugins, hooks or permissions, asks why their setup burns tokens, or runs /setup-doctor:doctor.Votes: 0GitHub stars: 2
- WrappedCreates a shareable usage summary card from the user's local coding agent session logs (sessions, tokens, estimated cost, streaks, busiest hours). Use when the user asks for their Wrapped, a usage recap or stats card, or how much they've used their coding agent.Votes: 0GitHub stars: 2
- DoctorAudits the user's AI coding agent setup and returns a 0 to 100 score with fixes. Use when the user asks to check, audit, score, lint or improve their instruction files, skills, MCP servers or hooks, or asks why their setup burns tokens.Votes: 0GitHub stars: 2
- WrappedCreates a shareable usage summary card from the user's local Cursor session logs (sessions, tokens, streaks, busiest hours). Use when the user asks for their Wrapped, a usage recap or stats card, or how much they've used Cursor.Votes: 0GitHub stars: 2
- DoctorAudits the user's AI coding agent setup and returns a 0 to 100 score with fixes. Use when the user asks to check, audit, score, lint or improve their instruction files, skills, MCP servers or hooks, or asks why their setup burns tokens.Votes: 0GitHub stars: 2
- Setup CareersSet up the careers section of the workspace for finding and applying to graduate roles, internships or placements. Imports the user's CV, interviews them for a search brief, picks job sites to check, and optionally schedules a daily or weekly role search. Use when the user says "set up careers", "help me find grad jobs / internships / placements", "set up job search", or when careers/BRIEF.md doesn't exist yet.Votes: 0GitHub stars: 4
- Getscribe Site SyncAudit and re-deploy the getscribe.dev marketing site whenever scribe ships a new release. Use this whenever a new scribe version is tagged or pushed, a new CHANGELOG entry lands, or the user says anything like "sync the site", "update getscribe.dev", "the site is stale", "check the site against the changelog", "did the landing page get updated for this release", or after running `git tag v*`. Also use it proactively when you notice the latest git tag / top CHANGELOG entry is newer than what t...Votes: 0GitHub stars: 66
- cvpr-figureCreate, revise and audit publication-grade pipeline, framework, teaser and module figures for CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, AAAI and ACL papers, and export them as Visio-editable .vsdx, PowerPoint-editable .pptx, plus SVG/PDF/PNG/EMF for LaTeX. Use for architecture diagrams, method overview figures, framework figures, pipeline diagrams, teaser/paradigm-comparison figures, attention and token diagrams, module zoom-ins, and 顶会论文配图、框架图、流程图、pipeline图、方法图、teaser图、 网络结构图、模型架构图、科研绘图、论文示意图、V...Votes: 0GitHub stars: 2
- Stack HopMove safely to the current stack head, append a stacked PR, or repair an authorised PR chain. Preserve local work, replay each child onto its actual parent as a linear range, publish batches through one push that gates every commit, and isolate a failed checkpoint. A context hop alone does not authorise remote stack repair.Votes: 0GitHub stars: 57
- SimplifyReview the changed code for reuse, simplification, efficiency and altitude cleanups in this repository, then apply the fixes. Quality only — it does not hunt for bugs; use /code-review for that. The method, its scripts and its cases live in this directory, so the skill works without any user-level skill pack.Votes: 0GitHub stars: 61
- Monitor Session Until IdleCritically supervise another Codex or agent session without taking it over, or audit a long, compacted or delegated session for commitments it forgot, narrowed or left unverified. Maintain executable closure, material-claim, and intervention ledgers; challenge unsupported claims before decision boundaries; correct proved errors; and stop only after accepted work and owned processes close. Use for long-running tasks, campaign watches, delegated reviews, and likely-mistake checks.Votes: 0GitHub stars: 57
- Launch RunLaunch authorised Anabasis runs or model pairs through one Bun TypeScript command, or stop an identified run under existing user authority. Owns preparation, exact condition checks, startup and stop mechanics; whole-run-investigation's outcome reference assesses whether stopping is justified.Votes: 0GitHub stars: 61
- Harness QueryInvoke an already-built Built Harness on one or more queries, without building a new one. Use when the operator points at a domain bundle and asks to run a task, a family, or a query they wrote, through it.Votes: 0GitHub stars: 57
- Final Harness AuditReview every harness version the Builder produced for one domain. Join workspace commits to iteration evidence, saved execution versions, measured batteries, and claims. Read-only over controller output.Votes: 0GitHub stars: 57
- Example SkillA copy-me template showing the SKILL.md format. Replace this description with a one-to-three sentence summary of WHAT the skill does and, critically, WHEN to use it — Claude reads only the name + description to decide whether to load a skill, so pack the trigger words here (e.g. "Use when the user says 'deploy', 'ship it', or asks to release a build"). This example skill does nothing; it exists to be duplicated.Votes: 0GitHub stars: 2
- Toolbox ContractThe micro-product contract for the IT Guy toolbox — acceptance criteria, directory layout, README template, registry schema, dry-run requirement, double-clickable wrappers, the evolution ladder, and the pattern catalogue used to offer a user automations they did not know to ask for. Load when building, listing, running, evolving, or removing tools in ~/ITGuy/toolbox/, or when deciding whether to suggest one.Votes: 0GitHub stars: 5
- Machine ProfileHow the IT guy remembers, refreshes, and retires what it knows about this machine — the profile schema, provenance classes, expiry by evidence, the belief ledger, demotion to history, the visit log, and undo manifests. Load when reading, writing, reviewing, or pruning anything in ~/ITGuy/.Votes: 0GitHub stars: 5