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.html using the installed html-playground skill.
- 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:
bash <skill-dir>/scripts/prepare.sh <slug>
Use its PLAYGROUND_DIR, DEBRIEFS_DIR, 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.md and 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.
1---2name: html-debrief3description: Use for interactive HTML debriefs or saved HTML findings/reports from the current task.4---5
6# HTML Debrief
7
8Persist current-task evidence as an interactive HTML report.
9
10Default to a standard desktop-browser layout. Do not implement or inspect responsive/mobile behavior unless the user
11asks.
12
13## Output and Authority
14
15- Output: `./.ai/debriefs/<slug>/index.html` using the installed `html-playground` skill.
16- Derive a short topical kebab-case slug when omitted.
17- Write only inside the selected debrief directory. If an inferred slug already exists, choose a collision-free semantic
18 qualifier, falling back to a timestamp suffix, and continue without overwriting. If the user explicitly supplied the
19 slug, stop and ask whether to overwrite or choose a new slug.
20- Use only evidence present in the current task: real findings, paths, verified locations, metrics, decisions, and
21 unresolved risks. Do not invent filler.
22
23## Workflow
24
251. Run the bundled preparer from the target repository:
26
27 ```sh
28 bash <skill-dir>/scripts/prepare.sh <slug>
29 ```
30
31 Use its `PLAYGROUND_DIR`, `DEBRIEFS_DIR`, `DEBRIEF_PATH`, and `EXISTS` output. When `EXISTS` is true for an inferred
32 slug, derive a unique slug and rerun the preparer before writing. When it is true for an explicit slug, request the
33 choice defined above. Relay dependency or slug-validation errors and stop.
34
352. Read the resolved HTML playground `SKILL.md` and exactly one matching template: diff review, document critique, code
36 map, concept map, data explorer, or design playground. Adapt its interaction model to the evidence; do not load every
37 template.
38
393. Build one self-contained HTML file with the playground's live controls, useful presets, evidence view,
40 natural-language prompt output, and copy feedback. Use no external dependencies.
41
424. Verify that every claim traces to the task transcript or tool evidence, the output contains no placeholders, and the
43 file renders in a desktop browser. Then run `open "$DEBRIEF_PATH"` and finish with `### 📊 Debrief ready — <title>`,
44 the clickable absolute path, `Opened in desktop browser`, and one compact line naming the evidence view and presets.
45
46Completion requires a non-placeholder HTML debrief at the selected path, evidence-grounded content, successful
47rendered/file inspection, and collision handling that never silently overwrites. Keep preparer `KEY=VALUE` output,
48dependency commands, paths, and slug errors exact and undecorated.
paulrberg