SKILL.md
HTML Debrief
Persist current-task evidence as an interactive HTML report.
Default to a standard desktop-browser layout. Do not implement or inspect responsive/mobile behavior unless the user asks.
Output and Authority
- Output:
./.ai/debriefs/<slug>/index.htmlusing the installedhtml-playgroundskill. - Derive a short topical kebab-case slug when omitted.
- Write only inside the selected debrief directory. If an inferred slug already exists, choose a collision-free semantic
qualifier, falling back to a timestamp suffix, and continue without overwriting. If the user explicitly supplied the slug, stop and ask whether to overwrite or choose a new slug.
- Use only evidence present in the current task: real findings, paths, verified locations, metrics, decisions, and
unresolved risks. Do not invent filler.
Workflow
- Run the bundled preparer from the target repository:
``sh bash <skill-dir>/scripts/prepare.sh <slug> ``
Use its PLAYGROUNDDIR, DEBRIEFSDIR, DEBRIEF_PATH, and EXISTS output. When EXISTS is true for an inferred slug, derive a unique slug and rerun the preparer before writing. When it is true for an explicit slug, request the choice defined above. Relay dependency or slug-validation errors and stop.
- Read the resolved HTML playground
SKILL.mdand exactly one matching template: diff review, document critique, code
map, concept map, data explorer, or design playground. Adapt its interaction model to the evidence; do not load every template.
- Build one self-contained HTML file with the playground's live controls, useful presets, evidence view,
natural-language prompt output, and copy feedback. Use no external dependencies.
- Verify that every claim traces to the task transcript or tool evidence, the output contains no placeholders, and the
file renders in a desktop browser. Then run open "$DEBRIEF_PATH" and finish with ### 📊 Debrief ready — <title>, the clickable absolute path, Opened in desktop browser, and one compact line naming the evidence view and presets.
Completion requires a non-placeholder HTML debrief at the selected path, evidence-grounded content, successful rendered/file inspection, and collision handling that never silently overwrites. Keep preparer KEY=VALUE output, dependency commands, paths, and slug errors exact and undecorated.