Explain
Skill control-decks/think-it-through/plugins/think-it-through/skills/explain
Explain the current HACP Working Object at the user's requested or apparent level with the minimum detail needed for understanding while preserving its claims and caveats. Use when the user invokes explain, asks for an explanation, or passes a result from another deck into EXPLAIN; never add an explanation silently.From its SKILL.md
npx -y skills add control-decks/think-it-through --skill explainAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.4 KB, 270 tokens by cl100k_base, as published. Nobody here has run it
💡 Think Explain
ID: think-it-through/explain
HACP: 0.4
Kind: presentation
Mode: render
Traits: read-only, semantic
Default Binding: Current Working Object, latest substantive result, or
clearly named subject
Accepts: hacp/content, hacp/result; accept success and blocked, and
defer pending unless the human asks to explain the proposed action
Produces: think-it-through/explanation
Duration: once
Effect: Explain the smallest unclear point at the human's requested or apparent level while preserving the object's claims, caveats, and uncertainty.
Limits: Do not invent evidence, change claims, advise, choose a direction, repeat the complete source, explain HACP automatically, or use more than one example unless requested.
Format
Begin the complete combo trace with > 🎯 **<binding>** → 💡 **EXPLAIN** when
used alone. Add → 💡 **EXPLAIN** after earlier cards in a combo.
Use Explanation as the only required heading. Add Example only when one
short example removes real ambiguity.
What ships with it: 2 files
18.3 KB alongside SKILL.md
agents/
- openai.yaml286 B
assets/
- icon.png18.0 KB
