Claude Skill

html-debrief

Use for interactive HTML debriefs or saved HTML findings/reports from the current task.

LLM Mart · 0 points · 0 0 0

Virus-scanned Reviewed automatically before listing.

Full trust report

Download paulrberg-agent-skills-skills_html-debrief-913232a.zip · 2 KB

paulrberg/agent-skills 94 7 forks MIT Updated 5h ago

Part of paulrberg/agent-skills — 42 skills

Install

skills CLI npx skills add https://github.com/PaulRBerg/agent-skills/tree/main/skills/html-debrief

Claude Code

claude plugin marketplace add https://llmmart.ai/marketplace.json && claude plugin install paulrberg-agent-skills@llmmart

Git git clone https://github.com/PaulRBerg/agent-skills.git

The skills CLI installs just this skill, for any of its supported agents. Claude Code installs the whole paulrberg/agent-skills collection as a plugin from our marketplace. Git is the plain clone.

Skill manifest

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.

Files (agent-skills)

agents

openai.yaml 42 B

policy:
  allow_implicit_invocation: true

scripts

prepare.sh 2.1 KB

#!/bin/bash
# html-debrief: validate slug, probe html-playground skill, create debriefs directory.
# Usage: prepare.sh <slug>
# Stdout (KEY=VALUE per line):
#   PLAYGROUND_DIR  absolute path to html-playground skill root
#   DEBRIEFS_DIR    absolute path to ./.ai/debriefs/<slug>
#   DEBRIEF_PATH    absolute path to ./.ai/debriefs/<slug>/index.html
#   EXISTS          true if DEBRIEF_PATH already exists, otherwise false
# Exit codes:
#   0  ok
#   2  html-playground skill not installed
#   3  invalid arguments or missing/bad slug

set -euo pipefail

SLUG=""
for arg in "$@"; do
  case "$arg" in
    -*)
      echo "Error: unknown flag: $arg" >&2
      echo "Usage: prepare.sh <kebab-case-slug>" >&2
      exit 3
      ;;
    *)
      if [ -n "$SLUG" ]; then
        echo "Error: unexpected extra argument: $arg" >&2
        exit 3
      fi
      SLUG="$arg"
      ;;
  esac
done

if [ -z "$SLUG" ]; then
  echo "Error: slug argument required" >&2
  echo "Usage: prepare.sh <kebab-case-slug>" >&2
  exit 3
fi

case "$SLUG" in
  *[!a-z0-9-]*|-*|*-)
    echo "Error: slug must be kebab-case (lowercase letters, digits, dashes; no leading/trailing dash): $SLUG" >&2
    exit 3
    ;;
esac

PLAYGROUND_DIR=""
for candidate in \
  ".agents/skills/html-playground" \
  ".claude/skills/html-playground" \
  "$HOME/.agents/skills/html-playground" \
  "$HOME/.claude/skills/html-playground"; do
  if [ -f "$candidate/SKILL.md" ]; then
    PLAYGROUND_DIR=$(cd "$candidate" && pwd -P)
    break
  fi
done

if [ -z "$PLAYGROUND_DIR" ]; then
  cat >&2 <<'EOF'
Error: the `html-playground` skill is not installed.

Install it with:
  bunx skills add PaulRBerg/agent-skills --skill html-playground --global

After installing, retry this skill.
EOF
  exit 2
fi

DEBRIEFS_DIR="$(pwd)/.ai/debriefs/$SLUG"
mkdir -p "$DEBRIEFS_DIR"
DEBRIEF_PATH="$DEBRIEFS_DIR/index.html"

if [ -f "$DEBRIEF_PATH" ]; then
  EXISTS="true"
else
  EXISTS="false"
fi

printf 'PLAYGROUND_DIR=%s\n' "$PLAYGROUND_DIR"
printf 'DEBRIEFS_DIR=%s\n'   "$DEBRIEFS_DIR"
printf 'DEBRIEF_PATH=%s\n'   "$DEBRIEF_PATH"
printf 'EXISTS=%s\n'         "$EXISTS"

SKILL.md 2.5 KB

---
argument-hint: "[<slug>]"
name: html-debrief
skill-dependencies:
  - html-playground
description: "Use for interactive HTML debriefs or saved HTML findings/reports from the current task."
---

# 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

1. Run the bundled preparer from the target repository:

   ```sh
   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.

2. 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.

3. 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.

4. 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.