sheal-check
Skill0 starsChanged 7 months agoMITView on GitHub
Run sheal health check and suggest fixes for detected issues. Checks tests, dependencies, environment, and session health.
- Reads credentials
- Installs packages
In this repository22 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- aif-analyzeSkill
- aif-enhanceSkill
- aif-evolveSkill
- aif-feedbackSkill
- aif-ingestSkill
- aif-learnSkill
- aif-pulseSkill
- aiframework-learnSkill
- aiframework-reviewSkill
- aiframework-shipSkill
- aif-readySkill
- aif-researchSkill
- aif-reviewSkill
- aif-shipSkill
- aif-statusSkill
- retroSkill
- sheal-askSkill
- sheal-driftSkill
- sheal-retroSkill
The file
We split this skill into the rules it gives an agent
2 rules. About 0 are common, 2 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
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
- Distinctive: line 19
Verify sheal is installed:
- Distinctive: line 45
If fixable issues found, propose fixes:
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
/sheal-check — Health Check
Prerequisites
Verify sheal is installed:
command -v sheal >/dev/null 2>&1 && sheal --version 2>/dev/null || echo "sheal not installed — run: npm install -g @liwala/sheal"Step 0: Telemetry (silent, non-blocking)
aiframework-telemetry skill_invoked skill=sheal-check 2>/dev/null || trueStep 1: Run Health Check
sheal check --format json --project . 2>/dev/null || echo '{"error": "sheal check failed"}'Step 2: Analyze Results
For each check result:
- pass: Note as healthy
- fail: Identify root cause and suggest fix
- skip: Note why it was skipped
Step 3: Auto-Fix (with approval)
If fixable issues found, propose fixes:
- Missing environment variables → suggest
.env.exampleupdates - Dependency issues → suggest install commands
- Configuration drift → suggest config updates
Step 4: Report
Output a summary table:
| Check | Status | Details |
| Tests | PASS/FAIL | ... |
| Dependencies | PASS/FAIL | ... |
| Environment | PASS/FAIL | ... |
| Session Health | PASS/FAIL | ... |
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.