AGENT SKILLS · ÉQUIPEMENT DE MISSION / obra

obra · Agent Skills

19 Skills avec une documentation substantielle et des sources vérifiées. Ouvrez une fiche pour lire les instructions originales et vérifier le paquet et son installation.

obra
Communauté

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, modifying behavior, or planning anything new, in software or out of it (a talk, a business, a renovation).

Installations totales
413,1 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes

Installations totales
315,4 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

writing-plans

Use when you have a spec or requirements for a multi-step task, before touching code

Installations totales
290 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

using-superpowers

Use when starting any conversation - establishes how to find and use skills, requiring skill invocation before ANY response including clarifying questions

Installations totales
276,3 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

requesting-code-review

Use when completing tasks, implementing major features, or before merging to verify work meets requirements

Installations totales
268,5 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

test-driven-development

Use when implementing any feature or bugfix, before writing implementation code

Installations totales
266,2 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

verification-before-completion

Use when about to claim work is complete, fixed, or passing, before committing or creating PRs - requires running verification commands and confirming output before making any success claims; evidence before assertions always

Installations totales
260 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

executing-plans

Use when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is available

Installations totales
249,7 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

subagent-driven-development

Use when executing implementation plans with independent tasks in the current session

Installations totales
244,3 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

receiving-code-review

Use when receiving code review feedback, before implementing suggestions, especially if feedback seems unclear or technically questionable - requires technical rigor and verification, not performative agreement or blind implementation

Installations totales
227,5 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Installations totales
224,1 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

writing-skills

Use when creating new skills, editing existing skills, or verifying skills work before deployment

Installations totales
224,1 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

using-git-worktrees

Use when starting feature work that needs isolation from current workspace or before executing implementation plans - ensures an isolated workspace exists via native tools or git worktree fallback

Installations totales
223 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

finishing-a-development-branch

Use when implementation is complete, all tests pass, and you need to decide how to integrate the work

Installations totales
220,4 k
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

diagnosing-superpowers

Use when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.

Installations / 24h
508
GitHub Stars
310,1 k
Mis à jour
29 oct.
obra
Communauté

remembering-conversations

You MUST invoke this skill before saying "I don't know," guessing, or treating any topic as new, no matter how trivial the question seems. It supplements other memory systems, which only hold partial records. Searching past conversations is the only way to recover what was actually said.

Installations / 1h
2
GitHub Stars
480
Mis à jour
10 sept.
obra
Communauté

writing-clearly-and-concisely

Apply Strunk's timeless writing rules to ANY prose humans will read—documentation, commit messages, error messages, explanations, reports, or UI text. Makes your writing clearer, stronger, and more professional.

Installations / 1h
2
GitHub Stars
606
Mis à jour
12 août
obra
Communauté

developing-claude-code-plugins

Use when working on Claude Code plugins (creating, modifying, testing, releasing, or maintaining) - provides streamlined workflows, patterns, and examples for the complete plugin lifecycle

Installations / 1h
1
GitHub Stars
142
Mis à jour
3 déc.
obra
Communauté

working-with-claude-code

Use when working with Claude Code CLI, plugins, hooks, MCP servers, skills, configuration, or any Claude Code feature - provides comprehensive official documentation for all aspects of Claude Code

Installations / 1h
1
GitHub Stars
142
Mis à jour
3 déc.