codemap

Included with Lifetime

$97 forever

Use for evidence-based codebase documentation. Walks the repo, builds a map of components + responsibilities + interconnections. Output is hand-curated markdown with diagrams. Variants — codemap-fast, codemap-diff, codemap-trust, codemap-export.

Writing & Docs

What this skill does


# codemap

Evidence-based codebase doc. Map of what exists, who depends on what, what each module does. Distinguishes confidence levels (proven by tests / inferred from usage / guessed).

## Variants

- **codemap** (this skill) — full pass, single repo
- **codemap-fast** — quick structural scan, no deep semantics
- **codemap-diff** — what changed between two refs (semantically, not just diff)
- **codemap-trust** — confidence/risk per module (which areas to trust, which to verify)
- **codemap-export** — machine-readable JSON output for tools

## Method (full codemap)

1. **Top-down survey.** Top-level dirs; one-line responsibility for each.
2. **Module inventory.** For each subdir:
   - LOC
   - Test coverage
   - Last-touched dates
   - Public API (exports / endpoints)
   - Internal deps (what does it import?)
   - External deps (npm packages used)
3. **Dependency graph.** Module-level. Mermaid.
4. **Hotspots.** High-churn × low-coverage = risk.
5. **Confidence labels** per module — high (tests + recent), med (works but uncovered), low (works but unstable).
6. **Output: ARCHITECTURE.md or codemap.md.**

## Output shape

```
# Codemap: <repo name>

## Top-level
- src/        — code
- tests/      — tests
- docs/       — hand-curated docs
- ...

## Modules

### src/memory/  (5,300 LOC, 96.86% cov, last-touched 2026-04-30)
**Responsibility:** persistent memory engine — daemon, MCP server, retrieval

**Public API:**
  - daemon: UDS server for capture
  - mcp/server: stdio MCP server
  - storage: dual-backend SQLite

**Imports from:** src/core, src/utils
**Imported by:** src/services (none yet)
**External deps:** better-sqlite3, node-sqlite3-wasm, gpt-tokenizer

**Confidence:** high (518 tests, recent)

### src/core/  (200 LOC, 100% cov, last-touched 2026-05-01)
**Responsibility:** plugin-wide primitives — config, paths, errors, logger
...

## Dependency graph

\`\`\`mermaid
graph TD
  Memory --> Core
  Memory --> Utils
  Services --> Core
  Services --> Utils
\`\`\`

## Hotspots
- (none — coverage strong, churn matched by tests)

## Confidence summary
- High:  4 modules (memory, core, utils, services)
- Med:   1 module (formatters — light usage)
- Low:   0 modules
```

## Rules

- **Cite LOC + coverage from real measurement,** not estimate.
- **Confidence labels with reasoning.** "High because <evidence>".
- **Hotspots are evidence-cited** — high churn from `git log`, low coverage from coverage report.
- **Don't bloat with file lists.** Module-level, not file-level.

## Anti-patterns

- File-by-file listing (use a tree command for that)
- Hotspots without evidence (just guessing)
- Confidence labels without reasoning
- Out-of-date diagrams (use `/codemap-diff` to verify)

## When NOT to use

- Tiny repo (manual scan faster)
- One module (just read it)
- Auto-generated doc tool already in place — augment, don't replace

## Subagent dispatch

- `Explore` for the survey
- `Bash` for `git log --shortstat`, `wc -l`, coverage extraction
- `general-purpose` for the synthesis

## Value over native CC

CC will list files. CC won't naturally produce evidence-cited confidence labels, dependency graphs, hotspot analysis. The evidence-based shape IS the value.

Files: 1

Size: 3.4 KB

Complexity: 8/100

Category: Writing & Docs

Source: https://github.com/ialameh/sift-coder/tree/main/skills/docs/codemap

Related in Writing & Docs

jax-development

Included

Use this skill when the user is writing, debugging, profiling, refactoring, reviewing, benchmarking, parallelising, exporting, or explaining JAX code, or when they mention JAX, jax.numpy, jit, grad, value_and_grad, vmap, scan, lax, random keys, pytrees, jax.Array, sharding, Mesh, PartitionSpec, NamedSharding, pmap, shard_map, Pallas, XLA, StableHLO, checkify, profiler, or the JAX repo. It helps turn NumPy or PyTorch-style code into pure functional JAX, fix tracer/control-flow/shape/PRNG bugs, remove recompiles and host-device syncs, choose transforms and sharding strategies, inspect jaxpr/lowering/IR, and benchmark compiled code correctly.

Writing & Docsscripts

nature-article-writer

Included

Drafts, rewrites, diagnostically critiques, and style-calibrates primary research manuscripts for Nature and Nature Portfolio journals. Use when the user wants a Nature-style title, summary paragraph or abstract, introduction, results, discussion, methods, figure legends, presubmission enquiry, cover letter, reviewer response, or when a scientific draft sounds generic, jargon-heavy, structurally weak, or AI-ish and needs precise, broad-reader-friendly prose without inventing data, analyses, or references. Best for primary research articles and letters rather than reviews or press releases unless explicitly adapting one.

Writing & Docsscripts

deckrd

Included

Document-driven framework that derives requirements, specifications, implementation plans, and executable tasks from goals through structured AI dialogue. Use when user says "write requirements", "create spec", "plan implementation", "derive tasks", "structure this feature", "break down into tasks", or "document this module". Also use for reverse engineering existing code into docs (/deckrd rev). Do NOT use for direct code writing — use /deckrd-coder after tasks are generated. Do NOT use when the user only wants to run or fix existing code without planning.

Writing & Docsscripts

clinical-decision-support

Included

Generate professional clinical decision support (CDS) documents for pharmaceutical and clinical research settings, including patient cohort analyses (biomarker-stratified with outcomes) and treatment recommendation reports (evidence-based guidelines with decision algorithms). Supports GRADE evidence grading, statistical analysis (hazard ratios, survival curves, waterfall plots), biomarker integration, and regulatory compliance. Outputs publication-ready LaTeX/PDF format optimized for drug development, clinical research, and evidence synthesis.

Writing & Docsscripts

handling-sf-data

Included

Salesforce data operations with 130-point scoring. Use this skill to create, update, delete, bulk import/export, generate test data, and clean up org records using sf CLI and anonymous Apex. TRIGGER when: user creates test data, performs bulk import/export, uses sf data CLI commands, needs data factory patterns for Apex tests, or needs to seed/clean records in a Salesforce org. DO NOT TRIGGER when: SOQL query writing only (use querying-soql), Apex test execution (use running-apex-tests), or metadata deployment (use deploying-metadata).

Writing & Docsscripts

accelint-ac-to-playwright

Included

Convert and validate acceptance criteria for Playwright test automation. Use when user asks to (1) review/evaluate/check if AC are ready for automation, (2) assess if AC can be converted as-is, (3) validate AC quality for Playwright, (4) turn AC into tests, (5) generate tests from acceptance criteria, (6) convert .md bullets or .feature Gherkin files to Playwright specs, (7) create test automation from requirements. Handles both bullet-style markdown and Gherkin syntax with JSON test plan generation and validation.

Writing & Docsscripts