sheal-ask
Skill0 starsChanged 7 months agoMITView on GitHub
Query session history using natural language. Search past sessions for patterns, decisions, and context.
- 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-checkSkill
- sheal-driftSkill
- sheal-retroSkill
The file
Files
/sheal-ask — Query Session History
Usage
/sheal-ask "your question here"
Prerequisites
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-ask 2>/dev/null || trueStep 1: Query
sheal ask "$ARGUMENTS" --project . 2>/dev/null || echo "sheal ask failed — check installation"Step 2: Supplement with Local Sources
Also search:
tools/learnings/*-learnings.jsonlfor matching JSONL entriesvault/memory/decisions/for related decisionsvault/memory/notes/for related notesgit log --oneline -30 --grep="<keyword>"for related commits
Step 3: Synthesize
Combine sheal session history with local sources to provide a comprehensive answer. Present the most relevant findings first.
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.