agentleFS
joris887joris887/exosuit/.claude/skills/help-me/SKILL.md

help-me

Skill9 starsChanged 3 months agoMITView on GitHub

Natural language skill discovery — describe what you want to do and get matched to the right skill.

3 other projects use a version of this.

Adopted by

Most recently taken up by

The file

We split this skill into the rules it gives an agent

5 rules. 0 are common, 5 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 3 edited versions we read keep these.

  • 5

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    If the user's intent is ambiguous, present options using AskUserQuestion with descriptions explaining the workflow implications of each …

    line 107
  2. Distinctive:

    If no skill matches, suggest:

    line 109
  3. Distinctive:

    Always explain WHY a skill is recommended, not just WHAT it does

    line 117
  4. Distinctive:

    If the user describes a multi-step workflow, suggest the sequence (e.g., "/brainstorm → /ideate → /sprint-start → /story-cycle")

    line 118
  5. Distinctive:

    Prefer specific skills over generic advice

    line 119

“Common” is measured: kept by at least 6 in 10 of the 3 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

help-me

Finding the right skill for: $ARGUMENTS

Intent Matching

Map the user's natural language request to the most appropriate skill(s):

Development Workflow

User SaysSkillWhy
"start working", "begin", "new sprint"/sprint-startCreates a clean feature branch
"build", "implement", "add feature", "create", "deliver"/story-cycle <description>Full story delivery with TDD
"ship", "finish sprint", "create PR", "merge"/sprint-endQuality gates → PR → merge
"resume", "pick up where I left off", "continue"/continueSmart session resumption
"done for today", "end session", "save progress"/handoffStructured session handoff

Planning & Design

User SaysSkillWhy
"plan", "break down", "decompose", "stories"/ideate <idea>Decompose into backlog stories
"explore design", "compare approaches", "architect"/brainstorm <idea>Design exploration with alternatives
"research", "investigate", "compare technologies"/research <topic>Deep online research with citations

Testing & Quality

User SaysSkillWhy
"test plan", "prepare for testing"/manual-testGenerate test plan from changes
"found a bug", "test feedback", "this doesn't work"/testing-cycle <feedback>Classify and process test findings
"run UAT", "acceptance test"/UAT-cycle <test-case-id>Execute formal UAT test case
"verify UAT logic", "sense check"/claude-sense-checkBatch UAT code verification
"check code quality"/code-qualityComplexity, duplication, patterns
"security review", "audit security"/security-auditCWE checklist, secrets, injection
"check architecture"/architecture-checkModule boundaries, drift

Debugging & Recovery

User SaysSkillWhy
"debug", "error", "broken", "fix bug"/debug-session <error>5-phase structured debugging
"fix issue", "fix #42", "github issue"/fix-issue <number>GitHub issue → TDD fix → PR
"undo", "revert", "go back", "start over"/undo-workSafe rollback (3 levels)

Maintenance & Review

User SaysSkillWhy
"health check", "is framework ok"/doctorFramework health validation
"weekly check", "maintenance"/weekly-maintenanceComprehensive weekly review
"retrospective", "what worked"/retrospectiveSprint review with 4Ls
"backlog health", "review stories"/backlog-reviewBacklog quality analysis
"PR status", "check PRs"/pr-statusOpen PR status + actions
"upgrade framework"/framework-upgradeUpdate to newer version

Utility

User SaysSkillWhy
"commit"/commitConventional commit
"parallel", "worktree", "multiple stories"/parallel-workManage concurrent worktrees
"improve iteratively", "refine"/refine-loop "<task>"Iterative self-improvement
"optimize metric", "increase coverage"/optimize "<goal>"Metric-driven optimization
"create skill"/skill-createGenerate tech-specific skills
"test a skill"/skill-evalSkill testing and comparison
"remove framework"/uninstallClean framework removal
"status", "dashboard"/dashboardSprint status overview

Prompt Snippets (lightweight, no workflow)

User SaysSkillWhy
"review security of file"/review-security <file>Quick security review
"explain this pattern"/explain-pattern <pattern>Code pattern explanation
"suggest tests for file"/suggest-tests <file>Test case suggestions

Presentation

Based on the user's input, present the top 1-3 matching skills:

### Recommended

**`/skill-name <arguments>`** — [one-line description of what it does and when to use it]

### Also Consider

- `/other-skill` — [why this might also apply]

If the user's intent is ambiguous, present options using AskUserQuestion with descriptions explaining the workflow implications of each choice.

If no skill matches, suggest:

  • Direct conversation for simple questions
  • /brainstorm for complex open-ended exploration
  • /research for information gathering

Rules

  • This skill is READ-ONLY — it recommends, it doesn't execute
  • Always explain WHY a skill is recommended, not just WHAT it does
  • If the user describes a multi-step workflow, suggest the sequence (e.g., "/brainstorm → /ideate → /sprint-start → /story-cycle")
  • Prefer specific skills over generic advice

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.