Skip to main content
ClaudeWave
Skill50 estrellas del repoactualizado 1mo ago

crisp-report

Generate a beautiful single-file HTML report from the project's docs/ folder. Works after any CRISP phase, after Archaeology, or at sprint close in Execute. Triggers on "generate report", "export docs", "create HTML report", "share docs", or automatically at sprint close in CRISP Execute.

Instalar en Claude Code
Copiar
git clone --depth 1 https://github.com/radekamirko/C.R.I.S.P /tmp/crisp-report && cp -r /tmp/crisp-report/.claude/skills/crisp-report ~/.claude/skills/crisp-report
Después abre una sesión nueva de Claude Code; el skill carga automáticamente.

SKILL.md

# CRISP Report Generator

Converts all markdown files in `docs/` into a single self-contained HTML file — cards overview, click-through to full documents, beautiful dark theme, no dependencies.

---

## How to run

**Step 1: Check dependencies**

```bash
pip3 install markdown pygments
```

If pip3 isn't available, try: `python3 -m pip install markdown pygments`

**Step 2: Run the script**

```bash
python3 scripts/generate-report.py [docs_dir] [output_file]
```

Defaults:
- `docs_dir` → `./docs`
- `output_file` → `./crisp-report.html`

Examples:
```bash
# Default — reads ./docs, outputs ./crisp-report.html
python3 scripts/generate-report.py

# Custom paths
python3 scripts/generate-report.py ./docs ./reports/sprint-3-report.html
```

**Step 3: Open**

```bash
open crisp-report.html
```

Or share the file directly — it's fully self-contained. No server needed.

---

## What it produces

- **Overview page** — card grid, one card per document, grouped by section (Discovery / Spec / Archaeology / Execute)
- **Document pages** — click any card → full rendered document with proper typography, code highlighting, tables
- **Escape / Back** → returns to overview
- Direct URL linking via `#doc-id` hash — shareable links to specific docs

---

## When to run

- **End of CRISP Phase S** — before handing off to Execute. Share with stakeholders for review.
- **End of each sprint** — updated report alongside the sprint delta doc. The stakeholder report section is already in the HTML.
- **After CRISP Archaeology** — share the recovered docs with the client or team.
- **Any time** — "generate report" at any point in a CRISP session.

---

## Script location

`scripts/generate-report.py` in the project root (copied from the CRISP repo).

If the script doesn't exist in the project yet, instruct the user to copy it from the CRISP repo:
```bash
curl -o scripts/generate-report.py https://raw.githubusercontent.com/radekamirko/C.R.I.S.P/main/scripts/generate-report.py
```
Or copy it manually from `C.R.I.S.P/scripts/generate-report.py`.

---

## Output file naming convention

| When | Suggested name |
|---|---|
| Phase S complete | `crisp-report.html` |
| Sprint N close | `crisp-report-sprint-N.html` |
| Archaeology complete | `crisp-report-archaeology.html` |
| Ad hoc | `crisp-report.html` (overwrites) |

---

## Troubleshooting

**`ModuleNotFoundError: No module named 'markdown'`**
→ Run: `pip3 install markdown pygments --break-system-packages`

**`No markdown files found in docs/`**
→ Make sure you're running from the project root, or pass the correct path: `python3 scripts/generate-report.py ./path/to/docs`

**Docs are blank or broken**
→ Check that docs are valid UTF-8 markdown. The script skips files it can't read.
crisp-executeSkill

CRISP Execute — Sprint execution loop with change request management, security gates, product gates, and stakeholder reporting. Use after Phase S (Spec) is complete and crisp-state.json shows ready_for_execute: true. Triggers on "start sprint", "begin build", "execute", "sprint 1", "run sprints", or when handed off from crisp-orchestrator.

crisp-orchestratorSkill

CRISP session manager — detects project state and routes to the right entry point. Use /crisp to start or resume any CRISP engagement. Handles new projects (discovery), existing codebases (archaeology), active sprints (execute), and validation (prove). Reads docs/crisp-state.json to know where you are.

crisp-startSkill

Begin a CRISP product discovery session — Phase C (Clarify)

phase1-clarifySkill

The Mileva Method (CRISP) — Phase 1: Clarify. Problem definition, eliciting, painkiller test, buy vs build, AI justification gate, Go/No-Go. Use at the start of any AI implementation project. Triggers on "clarify", "phase 1", "start discovery", "define the problem", "what problem are we solving", or at the beginning of a new client engagement.

phase2-resultsSkill

The Mileva Method (CRISP) — Phase 2: Results. Outcome alignment, stakeholder register, baseline measurement, success metrics, tradeoff negotiation. Use after problem definition is complete. Triggers on "results", "phase 2", "define success", "success metrics", "what does done look like", or after Phase C exit checklist is complete.

phase3-investigateSkill

The Mileva Method (CRISP) — Phase 3: Investigate. Process mapping for existing or greenfield processes, user journey mapping, UX discovery, project goals, system architecture (integration map + data flow). Use after outcome alignment. Triggers on "investigate", "phase 3", "map the process", "process mapping", "user journey", "as-is process", or after Phase R exit checklist is complete.

phase4-specSkill

The Mileva Method (CRISP) — Phase 4: Spec. Full implementation readiness package including solution design, UX direction, tech stack, backlog, MVP prioritization, risk assessment, and AI architecture for Claude Code projects — CLAUDE.md, skill mapping, AI specs, sprint planning, quality gates. Triggers on "spec", "phase 4", "build ready", "implementation plan", "CLAUDE.md", "sprint planning", "backlog", "AI spec", or after Phase I exit checklist is complete.

phase5-proveSkill

The Mileva Method (CRISP) — Phase 5: Prove. Success validation against Phase R baseline metrics, test log review, and AI justification validation. Use after deployment. Triggers on "prove", "phase 5", "validate", "did it work", "success criteria", "measure results", or after go-live.