agentleFS
EpistatesEpistates/sparX/.claude/skills/test/SKILL.md

test

Skill3 starsChanged 7 months agoMITView on GitHub

Verify sparX setup is working correctly. Use when the user wants to check their installation, test skills, or troubleshoot setup issues.

  • Reads credentials

We split this skill into the rules it gives an agent

9 rules. 0 are common, 7 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 137 edited versions we read keep these.

  • 7

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

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

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Run all checks (or a subset if the user specifies).

    line 13
  2. Distinctive:

    Read CLAUDE.md and confirm it contains "Phoenix Algorithm"

    line 24
  3. Very specific:

    Check that reference/scoring.md exists

    line 25
  4. Very specific:

    Run a quick /hooks generation to prove the content pipeline works:

    line 30
  5. Distinctive:

    No engagement bait phrases

    line 39
  6. Distinctive:

    Check if the Remotion project exists:

    line 48
  7. Distinctive:

    Check if claude-in-chrome is available by attempting to get tab context:

    line 67
  8. Distinctive:

    Check environment for optional integrations:

    line 85
  9. Distinctive:

    Use ✅ for pass, ❌ for fail (with fix suggestion), ⬜ for not installed (optional).

    line 124

“Common” is measured: kept by at least 6 in 10 of the 137 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

Test sparX Setup

Quick verification that everything is wired up correctly. Runs a series of checks and reports status.

Process

Run all checks (or a subset if the user specifies). Present results as a checklist.

1. Core Setup

✅ / ❌  CLAUDE.md loaded — check that Phoenix algorithm context is available
✅ / ❌  Reference docs exist — check reference/scoring.md, reference/penalties.md, etc.
✅ / ❌  Skills discovered — list all skills Claude can see (should be 15)

How to verify:

  • Read CLAUDE.md and confirm it contains "Phoenix Algorithm"
  • Check that reference/scoring.md exists
  • List available skills and count them

2. Skill Smoke Test

Run a quick /hooks generation to prove the content pipeline works:

Generate 3 hooks for: "a new open-source developer tool"

Pass criteria:

  • Produces 3 distinct hooks
  • Each is under 280 characters
  • No engagement bait phrases
  • Phoenix Score block appears
✅ / ❌  Skill pipeline — /hooks produced scored output

3. Remotion (optional)

Check if the Remotion project exists:

ls marketing/remotion.config.ts 2>/dev/null
✅ / ❌  Remotion project — marketing/ directory with remotion.config.ts
✅ / ❌  Remotion skills — marketing/.claude/skills/remotion-best-practices/SKILL.md
✅ / ❌  Tailwind configured — marketing/tailwind.config.ts or similar

If not installed:

⬜  Remotion not installed — run: pnpm create video --blank marketing

4. Browser Integration (optional)

Check if claude-in-chrome is available by attempting to get tab context:

mcp__claude-in-chrome__tabs_context_mcp()
✅ / ❌  Chrome connection — claude-in-chrome responds
✅ / ❌  Can create tab — tabs_create_mcp succeeds

If not available:

⬜  Chrome not connected — install claude-in-chrome extension

5. Optional Integrations

Check environment for optional integrations:

✅ / ❌ / ⬜  OpenTweet MCP — check if opentweet tools are available
✅ / ❌ / ⬜  last30days — check if ~/.claude/skills/last30days/SKILL.md exists
✅ / ❌ / ⬜  X API — check if TWITTER_API_KEY env var is set

Output

Present a summary dashboard:

sparX Setup Report
══════════════════

Core
  ✅ CLAUDE.md loaded (Phoenix algorithm context)
  ✅ Reference docs (6/6 files)
  ✅ Skills discovered (15/15)
  ✅ Skill pipeline (hooks generated successfully)

Remotion
  ✅ Project exists (marketing/)
  ✅ Agent skills installed
  ✅ Tailwind configured

Browser (claude-in-chrome)
  ✅ Chrome connected
  ✅ Tab creation works

Optional Integrations
  ⬜ OpenTweet MCP (not configured — run /setup opentweet)
  ⬜ last30days (not installed — run /setup last30days)
  ⬜ X API (not configured — run /setup x-api)

Status: Ready to go! Core + Remotion + Browser all working.

Use ✅ for pass, ❌ for fail (with fix suggestion), ⬜ for not installed (optional).

Download now (ZIP)

  • Other versions164 projects use a version of this.

    Word for word · 0

    None found.

    Edited · 0

    None found.

    Wrote their own version · 164

    1. facebook/react★ 252ksame name
    2. react/react★ 251ksame name
    3. apache/skywalking★ 25ksame name
    4. livewire/livewire★ 24ksame name
    5. NVIDIA/TensorRT★ 13ksame name
    6. FalkorDB/FalkorDB★ 11ksame name
    7. FastLED/FastLED★ 7.5ksame name
    8. fleetdm/fleet★ 7ksame name
    9. parcadei/Continuous-Claude★ 3.9ksame name
    10. parcadei/Continuous-Claude-v2★ 3.9ksame name

    154 more not listed

    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.

  • Used alongsideProjects with it also use agent-context-isolation, agentica-infrastructure and 10 more.

    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.
  • In this repository15 other files it gives its agents.

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.