html-debrief
starsforks
How to install html-debrief?
paulrberg/agent-skills/html-debrief
$npx -y skills add PaulRBerg/agent-skills --skill html-debriefUse for interactive HTML debriefs or saved HTML findings/reports from the current task.
SKILL.md
| 1 | # HTML Debrief |
| 2 | |
| 3 | Persist evidence from the current task as an opinionated interactive HTML report. |
| 4 | |
| 5 | ## Output and Authority |
| 6 | |
| 7 | - Output: `./.ai/debriefs/<slug>/index.html` using the installed `html-playground` skill. |
| 8 | - Derive a short topical kebab-case slug when omitted. |
| 9 | - Write only inside the selected debrief directory. If the output exists, stop and ask whether to overwrite or choose a |
| 10 | new slug. |
| 11 | - Use only evidence present in the current task: real findings, paths, verified locations, metrics, decisions, and |
| 12 | unresolved risks. Do not invent filler. |
| 13 | |
| 14 | ## Workflow |
| 15 | |
| 16 | 1. Run the bundled preparer from the target repository: |
| 17 | |
| 18 | ```sh |
| 19 | bash <skill-dir>/scripts/prepare.sh <slug> |
| 20 | ``` |
| 21 | |
| 22 | Use its `PLAYGROUND_DIR`, `DEBRIEFS_DIR`, `DEBRIEF_PATH`, and `EXISTS` output. Relay dependency or slug errors and |
| 23 | stop. |
| 24 | |
| 25 | 2. Read the resolved HTML playground `SKILL.md` and exactly one matching template: diff review, document critique, code |
| 26 | map, concept map, data explorer, or design playground. Adapt its interaction model to the evidence; do not load every |
| 27 | template. |
| 28 | |
| 29 | 3. Build one self-contained HTML file with the playground's live controls, useful presets, evidence view, |
| 30 | natural-language prompt output, and copy feedback. Use no external dependencies. |
| 31 | |
| 32 | 4. Verify that every claim traces to the task transcript or tool evidence, the output contains no placeholders, and the |
| 33 | file opens/renders. Then run `open "$DEBRIEF_PATH"` and finish with `### 📊 Debrief ready — <title>`, the clickable |
| 34 | absolute path, `Opened in browser`, and one compact line naming the evidence view and presets. |
| 35 | |
| 36 | Completion requires a non-placeholder HTML debrief at the selected path, evidence-grounded content, successful |
| 37 | rendered/file inspection, and explicit overwrite handling. Keep preparer `KEY=VALUE` output, dependency commands, paths, |
| 38 | and slug errors exact and undecorated. |
People who liked this also viewed
6 picksType
- find-skillsHelps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skSkillsJul 2026
- grill-meA relentless interview to sharpen a plan or design.SkillsJul 2026
- vercel-react-best-practicesVercel's official collection of agent skillsSkillsJul 2026
- improve-codebase-architectureScan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.SkillsJul 2026
- setup-matt-pocock-skillsConfigure this repo for the engineering skills — set up its issue tracker, triage label vocabulary, and domain doc layout. Run once before first use of the other engineering skills.SkillsJul 2026
- triageMove issues and external PRs through a state machine of triage roles — categorise, verify, grill if needed, and write agent-ready briefs.SkillsJul 2026
