Skills.
Give your AI a better way to work.
A skill is a set of written instructions that teaches an AI how to do one job the way it should be done: review a pull request, plan a migration, write the release notes.
Install one here and it travels with your account into Claude, Claude Code, Cursor and every other client you sign in with.
Category: AI & models
9,019 results · page 59 of 301
- View details
dart-audit-agent-complianceSkillAI & models
DART Audit Agent Compliance: audit and fix gaps when agents miss or cannot discover documented rules
Ready to connect★ 1k
- View details
dart-model-upgradeSkillAI & models
DART Model Upgrade: audit and improve DART AI harness content and structure for model or coding-agent upgrades, including named models, reasoning modes, migrations, compatibility reviews, and visual simulation-debugging evaluations
Ready to connect★ 1k
- View details
coding-agent-standardsSkillAI & models
Defines practical standards for implementation-focused coding agents. Use when creating or editing code, especially when reliability, clarity, and low-risk delivery are required.
Ready to connect★ 1k
- View details
prompt-architectSkillAI & models
Designs clear, testable prompts for agent workflows. Use when creating new prompts, refining weak prompts, or establishing reusable prompting patterns.
Ready to connect★ 1k
- View details
verification-agentSkillAI & models
Provides a structured verification workflow for code and prompt outputs. Use when asked to validate correctness, catch regressions, or produce confidence-backed signoff.
Ready to connect★ 1k
- View details
auto-researchSkillAI & models
Deep strategic research engine — decomposes questions into parallel research threads, spawns multiple agents, and synthesizes into actionable strategic analysis
Ready to connect★ 1k
- View details
daily-journalSkillAI & models
A passive daily work journal that Claude keeps FOR you so you never have to write it yourself. Append short entries after meaningful work (what was done, what you focused on, artifacts touched) to 01-daily/journal/YYYY-MM-DD.md. Run a guided reflection at night or in the morning. Use when you run /d
Ready to connect★ 1k
- View details
harvestSkillAI & models
Capture durable session learnings, stage for human promotion to 05-knowledge/lizard, and propose skill/CLAUDE.md patches. Triggered by /harvest, SessionEnd hook staging, or nightly enhance. Never writes durable knowledge without your approval.
Ready to connect★ 1k
- View details
product-ui-tasteSkillAI & models
Anti-slop skill for PRODUCT UI - dashboards, data tables, forms, multi-step flows, settings, list/detail, app shells. The agent reads the surface, budgets the frame first, and ships dense interfaces that are correct at every edge case (overflow, long labels, empty/error/loading states, i18n expansio
Ready to connect★ 1k
- View details
retroSkillAI & models
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.
Ready to connect★ 1k
- View details
- View details
twmd-babelSkillAI & models
Multi-language batch sync (sovereign Babel tower) via the canonical SQUEEZE-MODELS-MAX-PIPELINE — priority schema (P0/P1/P2/P2.5/P3) + backend cascade + unified dispatcher babel-dispatch.py. TRIGGER when: user says "巴別塔", "多語 batch", "多語同步", "跑 babel", "繼續 babel".
Ready to connect★ 1k
- View details
twmd-batch-auditSkillAI & models
Audit sub-agent batch for the three default cheating patterns (cross-pollination commits / merged commits / missing落檔) per DNA #42. TRIGGER when: user says "batch audit", "sub-agent 後驗證", "agent 偷吃步檢查", or after running parallel sub-agent batches.
Ready to connect★ 1k
- View details
twmd-benchSkillAI & models
Sovereignty-Bench-TW measurement via canonical BENCH-PIPELINE. TRIGGER when: user says "跑 bench", "Sovereignty-Bench", "加新 model", "bench-pipeline".
Ready to connect★ 1k
- View details
twmd-embeddingsSkillAI & models
Rebuild the bge-m3 semantic index via canonical EMBEDDING-PIPELINE — one keystone build feeds reader related-articles (src/data/related) + RAG vectors (public/api/rag). Sovereignty-preserving: embeddings computed in-house (mac-m4max local primary, GPU fleet fallback), never outsourced. TRIGGER when:
Ready to connect★ 1k
- View details
twmd-routine-syncSkillAI & models
讓這台機器的 routine prompt 與排程設定跟 git 的 routine SSOT 對齊。 Routine twmd-routine-sync fires 05:30 daily（晨鏈之前）; manual via "/twmd-routine-sync" or "同步 routine" or "routine 對齊". TRIGGER when: routine twmd-routine-sync fires / user says "同步 routine" / "routine 三層對賬" / 剛 ship 完 routine 改動要讓其他機器跟上.
Ready to connect★ 1k
- View details
sync-visionSkillAI & models
Sync root VISION.md from changed human and agent inputs; use when project taste, doctrine, or maintainer judgment should learn from recent plans, docs, skills, reviews, or repeated misses.
Ready to connect★ 1k
- View details
clean-gone-branchesSkillAI & models
This skill should be used when user asks to "clean gone branches", "remove deleted local branches", "prune branches removed from remote", or explicitly invokes "clean-gone-branches".
Ready to connect★ 1k
- View details
codex-advisorSkillAI & models
This skill should be used when the user asks for a "GPT second opinion", wants a "cross-model review", needs to "check a plan before committing", wants another view after repeated failures, or explicitly invokes "codex-advisor".
Ready to connect★ 1k
- View details
fable-advisorSkillAI & models
This skill should be used when the user asks for a "Fable second opinion", wants to "check a plan before committing", needs another view after repeated failures, or explicitly invokes "fable-advisor".
Ready to connect★ 1k
- View details
programmatic-seoSkillAI & models
Use when planning many similar pages from a template and a data set: choosing the pattern, deciding whether the data can carry it, and avoiding the thin-content failure that gets page sets deindexed.
Ready to connect★ 1k
- View details
python-guidelinesSkillAI & models
This skill should be used when writing, reviewing, or refactoring Python code. Covers code integration, idiomatic patterns, docstring formatting, anti-abstraction rules, and software engineering basics.
Ready to connect★ 1k
- View details
resolve-pr-commentsSkillAI & models
This skill should be used when user asks to "address PR comments", "resolve PR feedback", "handle review comments", "fix PR issues", "respond to PR review", or explicitly invokes "resolve-pr-comments".
Ready to connect★ 1k
- View details
review-overleafSkillAI & models
This skill should be used when user asks to "fetch overleaf review comments", "address overleaf reviews", "apply overleaf comments", "review my overleaf paper", "sync overleaf feedback to local", "what comments are on my overleaf doc", or wants to act on Overleaf reviewer feedback in a local git-tra
Ready to connect★ 1k
- View details
review-prSkillAI & models
This skill should be used when user asks to "review a PR", "review pull request", "review this pr", "code review this PR", "check PR #N", provides a GitHub PR URL, or explicitly invokes "review-pr".
Ready to connect★ 1k
- View details
schemaSkillAI & models
Use when adding, fixing, or reviewing structured data: JSON-LD for articles, products, FAQs, breadcrumbs, organizations, and local businesses, and what to do when markup doesn't earn a rich result.
Ready to connect★ 1k
- View details
simplifySkillAI & models
This skill should be used when the user asks to "simplify", "clean up the diff", "run simplify", "simplify the changes", "review changed code for cleanup", explicitly invokes "/simplify", or asks to "commit without simplify", "skip simplify for this commit", or "commit this but skip simplify". Revie
Ready to connect★ 1k
- View details
site-architectureSkillAI & models
Use when planning or restructuring what pages a site has and how they connect: hierarchy, navigation, URL patterns, breadcrumbs, and internal linking. Not for XML sitemaps, which are in seo-audit.
Ready to connect★ 1k
- View details
- View details
update-pr-summarySkillAI & models
This skill should be used when user asks to "update PR summary", "update PR description", "rewrite PR body", "refresh PR title and body", or explicitly invokes "update-pr-summary".
Ready to connect★ 1k
What is a skill?
A skill is plain text, usually a SKILL.md file and the scripts it refers to, written for an AI rather than for a person. It carries the steps, the house rules and the examples a good answer needs, so you stop pasting the same briefing into every new chat.
54,764 of the 55,196 skills listed here can be served through ahel today, and they come from public repositories. Each one has its own page with the instructions themselves on it, so you can read what a skill will tell your AI to do before you install it.
Install one and every AI you use gets it
Installing a skill adds it to your gateway and turns it on in the same step. Claude Code surfaces it as a slash command; any client can read the full instructions with the skill_read tool.
Nothing is copied into a project folder. The instructions are served from your account, so the same skill is there in every AI you connect, and turning it off removes it from all of them at once.