Use when working in a repository that uses bd or Beads for durable project task tracking, issue dependencies, blocker management, multi-session handoff, or shared work memory. Trigger when the user asks to find ready work, claim or close tasks, create follow-up work, inspect blockers, recover project context, or choose between local planning and persistent project tracking.
55 projects use a version of this
1948d agoReviewMountCreate a free account to mount
Record a call or meeting on this computer with akou and answer questions about it while it runs, or transcribe an audio file. Use when the user says record this call or meeting, starts a call, names a speaker, spells a word, asks what was said, decided or is being discussed, or hands over a recording or voice note to transcribe.
1948d agoReviewMountCreate a free account to mount
Teach akou the names and terms of the user's world, so recordings spell them right. Use before a call when the user shares an invite, when the user asks to prepare akou's vocabulary, or after a call to turn the words it got wrong into entries. Every word you find ends as a proposal the user approves; you never confirm one yourself.
1948d agoReviewMountCreate a free account to mount
Explain work, a system or a situation to the user in plain words with real names, so they understand it on one read. Use when the user asks to explain like a 5yo, says eli5, or says they do not understand what was done or where things stand.
Open a pull request whose title says why the change matters and whose body opens with the problem in the requester's words. Use when asked to file, open, raise or create a PR, or to rewrite a PR's title or description.
Drive a repository to done with sergio-loop, then keep improving it with refine-loop at a descending theta. Use only when the user explicitly invokes full-loop.
Make a video, screen recording or demo clip play inline inside a GitHub Markdown file, pull request or release. Use when a video must play in the README or a PR, when asked to embed a video or add an inline player, or when a committed video renders blank.
Plan and carry out where an open-source repository gets listed so people find it, from GitHub itself to registries, directories, public catalogues, media, communities and funding. Use when asked to grow, promote or publicise a repo, or where else it could be listed.
Lay a decision out for the user so one word answers it, recommendation and pros and cons first, then how the thing works and what each choice changes. Use when the user says help-decide, asks for pros vs cons, or answers a question with "don't understand, explain".
Implements a requested change with the smallest complete diff, splitting genuinely independent work across parallel agents with non-overlapping file ownership, then integrates and verifies it. Use when invoked explicitly to build a feature or change.
Investigates a bug or unexpected behavior from reproduction to root cause with a panel of independent hypothesis agents, then fixes it only when the request asks for a fix. Use when invoked explicitly to debug, diagnose, or fix a reported failure.
Answers a question from the team's own record (chat archives, call transcripts, tickets, wiki pages, notes, any mix) through a knowledge-base adapter you fill in. Read-only, never from memory, every claim cited to the source it came from. Use when invoked explicitly to find what the team said or decided, who owns something, or whether a plan contradicts an earlier decision.
Reviews a pull request the way the team's reviewers do, grounded in reviewer learnings and past decisions captured in your knowledge base, verifies every finding against the code, and reports a severity-ranked review. Reports only; never posts, approves or merges without explicit instruction. Use when invoked explicitly on a PR, your own before requesting review or a teammate's.
Researches a question with independent parallel specialists that gather evidence from the code, its history, and primary sources, then synthesizes a ranked, cited answer. Use when invoked explicitly for research before a decision.
Audits a whole codebase in bounded waves of independent parallel auditors, publishes every verified finding ranked by severity, and applies only safe, in-scope repairs. Use when invoked explicitly for a codebase health review.
Review one or more pull requests as a single Workflow run (three lenses, one fixer, one adversarial verifier), comment the plan on each PR, push the fixes, then merge or close. Use when asked to review, fix up or merge a PR, or on "review-pr".
Bring cut-off work back exactly where it stopped after a usage limit, a crash, a restart or a compaction, without doing anything twice. Use when a session resumes after a limit or crash, when agents or background tasks died mid-work, or when asked to continue, resume or revive.
Runs a durable inspect/plan, implement, verify, and fresh-review loop toward an explicit repository goal, with optional lease-backed coordination across sessions. Use only when the user explicitly invokes sergio-loop.
A folder with a SKILL.md file: a name, a description of when to use it, and instructions. Claude loads a skill only when the task matches its description.
How do I use one I find here?
Copy the folder into your project's .claude/skills/ directory, or into your own skills folder to use it everywhere.
What do the warnings mean?
We read each file for commands that read secrets, delete things or pipe downloads into a shell, and say so before you copy it. No warning is not a promise that a file is safe.
Which skills worked for people?
Open a skill to see its discussion. Reports from people and their agents are coming.