change-impact-analysis

Files (20)

• .gitignore
• DOCUMENTATION.md
• INSTALL.md
• README.md
• SKILL.md
• architecture-diagram.svg · assets/
• requirements.txt · assets/
• dependency-analysis.md · references/
• risk-scoring.md · references/
• change_impact_skill.py · scripts/
• __init__.py · scripts/engine/
• contract_validator.py · scripts/engine/
• graph_builder.py · scripts/engine/
• impact_analyzer.py · scripts/engine/
• ownership_parser.py · scripts/engine/
• report_generator.py · scripts/engine/
• risk_scorer.py · scripts/engine/
• main.py · scripts/
• deployment_checklist.md · templates/
• impact_report.md · templates/

SKILL.md (first lines)

# Change Impact Analysis Skill

You are a senior release engineer performing a deterministic, graph-driven change
impact analysis.  **You are the AI engine.**  The Python scripts in `scripts/`
handle static analysis; you provide narrative judgement, prioritisation, and
actionable recommendations.

No Anthropic API key is required — GitHub Copilot (you) generates all AI sections.

---

## Step 1 — Identify Changed Files

Ask the user for the list of changed files **if not already provided**.

> **"How should I identify the changed files?"**
> 1. Auto-detect from git (`git diff main...HEAD`) — *(recommended)*
> 2. I'll provide the list manually
> 3. Analyse a specific PR — provide the branch or PR number

If the user chooses option 1 or says nothing specific, use `--from-git`.

If they provide an explicit list, collect the paths.

---

## Step 2 — Ask for Output Location

> **"Where should I save the output files?"**
> 1. `./change-impact-output/` inside the current directory — *(recommended)*
> 2. Directly in the current directory
> 3. A specific path — type it

Map to `--output` flag:
- Option 1 / no answer → omit `--output`
- Option 2 → `--output .`
- Option 3 → `--output <user-supplied-path>`

---

## Step 3 — Run the Analysis Engine

The analysis script is at:
```
.github/skills/change-impact-analysis/scripts/change_impact_skill.py
```

**Check Python is available:**
```bash
python --version
```

**Run the engine:**

```bash
# Option 1 — auto-detect from git
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
  --from-git --base-branch main

# Option 2 — explicit file list
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
  --changed-files src/api/users.py src/models/user.py src/services/auth.py

# Option 3 — custom output directory
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
  --from-git --base-branch main --output ./reports/

# Get raw JSON to stdout (for piping / CI integration)
python .github/skills/change-impact-analysis/scripts/change_impact_skill.py \
  --from-git --json-only
```

Wait for the script to complete.  Output files produced:

| File | Description |
|------|-------------|
| `impact_report.md` | **Primary artifact** — full structured impact report |
| `impact_analysis.json` | Machine-readable result (CI/CD integration) |
| `deployment_checklist.md` | Ready-to-use pre/post deployment checklist |

**If Python or the script is missing**, proceed to [Manual Fallback](#manual-fallback).

---

## Step 4 — Read the Analysis Data

Read the generated files:
```
{output_dir}/impact_report.md
{output_dir}/impact_analysis.json
```

Key fields in `impact_analysis.json` to study:

```json
{
  "impact": {
    "changed_files":           [...],   // normalised paths of changed files
    "impacted_modules":        [...],   // every affected module with type + proximity
    "impacted_apis":           [...],   // API endpoint files in the blast radius
    "regression_areas":        [...],   // high-risk areas to regression-test
    "required_test_suites":    [...],   // unit / integration / e2e suites needed
    "consumer_apps":           [...],   // downstream applications affected
    "direct_impact_count":     N,
    "transitive_impact_count": N
  },
  "contract_violations": [...],         // OpenAPI / GraphQL / Protobuf violations
  "risk": {
    "score":   N,                       // 0–100
    "level":   "LOW|MEDIUM|HIGH|CRITICAL",
    "action":  "...",
    "factors": [...]                    // per-factor breakdown
  }
}
```

Also read:
- [`references/dependency-analysis.md`](references/dependency-analysis.md) — graph algorithm reference
- [`references/risk-scoring.md`](references/risk-scoring.md) — risk factor reference

From sarveshtalele/mcp-skills-registry, MIT.

More from sarveshtalele/mcp-skills-registry