using-skills
Skill0 starsChanged 22 days agoMITView on GitHub
Use at the start of any development conversation or task: check which skill applies BEFORE responding or acting, and follow the standard pipeline from idea to merged code. Not for writing or editing a skill, that is writing-skills.
8 other projects use a version of this, 1 of them edited.
Adopted by
Most recently taken up by
- axiomantic/spellbooktheir own version, first seen Nov 1, 2026
- KMaruthi2002/universal-llm-skillstheir own version, first seen Oct 25, 2026
- PracticalSwan/agent-skillstheir own version, first seen Oct 19, 2026
- TylerAkins/ai-agent-skillstheir own version, first seen Oct 15, 2026
- int2t05/engineering-skillstheir own version, first seen Oct 15, 2026
- microsoft/FluidFrameworktheir own version, first seen Oct 13, 2026
Used with
Projects with it also use git-workflow.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
Microsoft AzureSkillgit-workflow
Squad branching model: dev-first workflow with insiders preview channel
Also in 3 projects that use this
Other versions8 projects use a version of this.
Word for word · 0
None found.
Edited · 1
- aaddrick/claude-pipeline★ 12813% same
Wrote their own version · 7
- microsoft/FluidFramework★ 4.9ksame name
- PracticalSwan/agent-skills★ 22same name
- axiomantic/spellbook★ 11same name
- int2t05/engineering-skills★ 3same name
- KMaruthi2002/universal-llm-skills★ 1same name
- TylerAkins/ai-agent-skills★ 1same name
- nilssonr/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository25 other files it gives its agents.
- AGENTS.mdAGENTS.md
- brainstorming-designSkill
- branch-lifecycleSkill
- bug-feedback-loopSkill
- codebase-designSkill
- code-review-disciplineSkill
- domain-modelingSkill
- failure-classesSkill
- git-safetySkill
- grillingSkill
- handoffSkill
- ops-safetySkill
- prototypeSkill
- quality-floorSkill
- researchSkill
- subagent-driven-devSkill
- systematic-debuggingSkill
- terse-modeSkill
- test-driven-developmentSkill
- ui-designSkill
- verification-before-completionSkill
- vetting-third-partySkill
- writing-plansSkill
- writing-skillsSkill
- zoom-outSkill
The file
Files
Using Skills (skills-first workflow)
The Rule
If there is even a 1% chance a skill applies to what you are doing, invoke it BEFORE any response or action — including clarifying questions, exploring the codebase, or checking files. If it turns out wrong for the situation, you don't have to use it.
Announce "Using [skill] to [purpose]" and follow the skill exactly. If it has a checklist, create a todo per item.
How to invoke a skill: if your tool loads skills natively (a Skill tool, /skill-name, automatic loading), use that. Otherwise open <skills-dir>/<name>/SKILL.md with your file-read tool and follow it; paths inside a skill (scripts/, references/) are relative to that skill's folder; run its scripts from the project root by full path (<skill-dir>/scripts/...).
Skill Priority
Process skills come first — they set the approach; implementation skills carry it out.
- "Let's build X" →
brainstorming-designfirst, then implementation. - "Fix this bug" →
systematic-debuggingfirst, then domain skills.
User instructions (direct requests, then the project's AGENTS.md / CLAUDE.md / rules files) take precedence over skills, which override default behavior.
The Standard Pipeline
- brainstorming-design — refine idea into an approved design/spec. No code before approval.
- branch-lifecycle — isolated workspace (worktree/branch), clean test baseline.
- writing-plans — bite-sized tasks (2-5 min each) with exact paths, code, and verification.
- subagent-driven-dev — fresh subagent per task with two-stage review; or inline execution with checkpoints.
- test-driven-development — RED-GREEN-REFACTOR inside every task.
- code-review-discipline — review between tasks; critical issues block progress.
- verification-before-completion — evidence before any success claim.
- branch-lifecycle (finish) — verify tests, present merge/PR/keep/discard options.
These are mandatory workflows, not suggestions.
Red Flags — you are rationalizing
| Thought | Reality |
| "This is just a simple question" | Questions are tasks. Check for skills. |
| "I need more context first" | Skill check comes BEFORE clarifying questions. |
| "Let me explore the codebase first" | Skills tell you HOW to explore. |
| "This doesn't need a formal skill" | If a skill exists, use it. |
| "The skill is overkill" | Simple things become complex. Use it. |
| "I remember this skill" | Skills evolve. Read the current version. |
Distilled from obra/superpowers (MIT © Jesse Vincent / Prime Radiant), using-superpowers v6.1.0 @ f268f7c. See SOURCES.md.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.