Comments
Code comments and annotations
deep-teach
by congmnguyen
Tutor the user toward deep understanding of a topic, codebase, paper, artifact, or concept through incremental explanation, active recall, and verification. Use when the user asks to be taught, wants to understand something deeply, says "teach me", "walk me through", "explain until I get it", "quiz me", asks for ELI5/ELI14/intern-level teaching, or needs a learning session instead of a one-off answer. Skip for simple factual answers or implementation tasks where teaching is not requested.
write-pr-description
by warpdotdev
Writes the body of a pull request - the summary, the repository template sections, and reviewer guidance such as a recommended reading order and focus areas. Use whenever drafting or revising a PR description, filling in a repository's PR template, refreshing a description that no longer matches the branch, or preparing a branch for review. Use it even when the user only says "open a PR", "put this up for review", or "write this up" without naming the description.
moltbook
by zqm0779
AI Agent的社交网络. 发布帖子、评论、点赞和创建社区。当用户明确要求时才会使用，否则不会使用。
quiz
by TakaGoto
"Test your understanding of a RAG concept"
review-pending-pr-reviews
by nrwl
Review, grill, edit, and post pending PR review drafts saved by /review-pr (or its batch/cron runners). Lists drafts that have not yet been posted, walks the maintainer through each finding, then posts, closes, or discards. Use when the user says "post my pending reviews", "what reviews are waiting", "go through the review outbox", or invokes /review-pending-pr-reviews.
SKILL.md — Smart Plant 1 Comply Spec Workflow
by theopensoft-RD
ดูรายละเอียด status + cross-reference: knowledge_base/sections.json + knowledge_base/KB.md
interview-task
by polarsource
Prepare an interview task for a candidate, as part of our hiring process.
humanizer
by harperreed
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, passive voice, negative parallelisms, and filler phrases.
substack-notes-scraper
by mohitagw15856
"Scrapes a Substack Notes page and exports engagement data to a formatted .xlsx file. Use when asked to download, analyse, or export Substack Notes performance data including likes, comments, and restacks. Produces a formatted spreadsheet with conditional formatting, summary stats, and per-note engagement metrics."
by imoonkey
```
algorithms-and-data-structures
by ParamChordiya
Enforces complexity analysis, correct data structure selection, vectorization, and algorithm implementation discipline at principal-engineer level.
codex-pr-review
by johnpsasser
Review a pull request using OpenAI Codex (gpt-5.3-codex). Use when the user wants an external AI code review via Codex, a second opinion on a PR, or a cross-model review. Supports auto-detection of current branch PR or explicit PR number/URL.
tiramisu-create-agent
by iamhansi
Create new agents in Paperclip with governance-aware hiring. Use when you need to inspect adapter configuration options, compare existing agent configs, draft a new agent prompt/config, and submit a hire request.
by imoonkey
```
reuse-check
by polarsource
Check a diff for code that reinvents something Polar already has — a kit helper, a shared Pydantic type, a repository method, an Orbit component, an existing model property. Use before opening a PR, when reviewing a diff, or when the user asks whether a new helper, validator, type or utility already exists in the codebase.
human-readable-refactor
by khasky
Behavior-preserving cleanup of AI-like or vibe-coded code: remove noisy comments, improve names, simplify control flow, remove dead/duplicated/speculative code, and align with local repo style.
workflow-integration-gitlab
by cuioss
GitLab provider for MR review workflows — fetch comments, triage, and respond to review feedback via glab CLI
reproduce-bug-report
by warpdotdev
Launch Oz cloud agents with computer use to reproduce UI-focused bug reports, capture visual evidence (a screen recording by default), and report reproduction findings. Use when investigating a specific interactive or visual bug from an issue, ticket, support report, or prompt.
python-style
by janjaszczak
Enforce consistent Python typing (type hints + return types), concise Google-style docstrings, PEP 8/Black formatting, and unit tests when creating or editing Python code. Use when working on .py files, Python APIs, refactors, or bug fixes where maintainability and correctness matter.
Bulk RNAseq differential expression (DeSeq2)
by BioTender-max
A curated collection of AI agent skills for biomedical research, covering genomics, proteomics, single-cell analysis, clinical AI, and protein design.
classification-policy
by Hack23
Risk-based data and asset classification framework: PUBLIC, INTERNAL, CONFIDENTIAL, RESTRICTED aligned with ISO 27001 A.5.12 and CIA triad
skill-installer
by yuanxiao0115
Install Codex skills into $CODEX_HOME/skills from a curated list or a GitHub repo path. Use when a user asks to list installable skills, install a curated skill, or install a skill from another repo (including private repos).
moltoverflow
by moltoverflow
Search and contribute to the moltoverflow knowledge base for programming packages. Use when you encounter errors, need solutions for a specific package/language, or want to share knowledge that could help other agents.
by imoonkey
Upstream typos: destory (not destroy) — unbookmarkPost POSTs to /ajax/statuses/destoryFavorites and unfollowUser POSTs to /ajax/friendships/destory. Both spellings are wrong (Weibo's typo); using the "correct" destroy returns HTML 404. Param name is also asymmetric — followUser takes friend_uid, unfollowUser takes uid.