update-docs
Update documentation across the repo after API changes. Finds stale references in docs, examples, docstrings, and fixes them.
Works with
---
name: update-docs
description: Update documentation across the repo after API changes. Finds stale references in docs, examples, docstrings, and fixes them.
license: BSD-3-Clause
---
# /update-docs
Find and fix stale documentation after API changes.
## EXECUTE THESE STEPS NOW
When this skill is invoked, you MUST execute these steps immediately.
### Step 1: Identify Changed Files
Run:
```bash
git diff --name-only main...HEAD -- '*.py'
```
If no changes are found relative to main (e.g., on main or no upstream), fall back to:
```bash
git diff --name-only HEAD~1 -- '*.py'
```
If that also fails, ask the user which files changed.
Collect the list of changed Python files.
### Step 2: Extract API Changes
For each changed .py file, compare old vs new signatures using the same
ref that worked in Step 1:
```bash
# If Step 1 used main...HEAD:
git diff main...HEAD -- <file>
# If Step 1 fell back to HEAD~1:
git diff HEAD~1 -- <file>
```
Look for changes to:
- Function/method signatures (def lines)
- Class names and __init__ signatures
- Module-level constants and type aliases
- Removed or renamed public symbols
Build a list of `(old_signature, new_signature)` pairs.
If no API changes are found (only internal logic changes), report
"No API changes detected — no docs update needed" and stop.
### Step 3: Spawn Docs Updater Agent
Use the Task tool to spawn the docs-updater agent. IMPORTANT: the
`description` field MUST contain "docs-updater" so the SubagentStop
hook fires correctly.
```
Task tool:
subagent_type: general-purpose
description: "docs-updater propagation"
prompt: |
You are a docs-updater agent. Read .claude/agents/docs-updater.md
for your full instructions.
Here are the API changes to propagate:
Changed files: <list>
API changes:
- `old` → `new`
...
Search the entire repo for references to the old APIs and update
them to match the new signatures. Follow the process in
.claude/agents/docs-updater.md exactly.
```
### Step 4: Review Results
After the agent returns:
- Review the update report
- Verify no test files were touched
- Verify changes are minimal and correct
Report the summary to the user.
---
## When to Use
- After `/implement` when API signatures changed
- Before `/pre-submit-pr` to ensure docs are fresh
- When refactoring public APIs
## When NOT to Use
- Internal-only changes (no public API affected)
- Test-only changes
- Documentation-only changes (no code changed)
## Workflow Integration
```
/write-tests → Red (failing tests)
/implement → Green (passing tests)
/update-docs → Fix stale docs across repo ← THIS SKILL
/simplify → Refactor (optional)
/pre-submit-pr → Validate before PR
```More Writing & Documentation skills
paper-context-resolver
lllllllama/rigorpilot-skills
Rigor Paper Context helper for README-first deep learning repo reproduction. Use only when the README and repository files leave a narrow reproduction-critical gap and the task is to resolve a specific paper detail such as dataset split, preprocessing, evaluation protocol, checkpoint mapping, or runtime assumption from primary paper sources while recording conflicts. Do not use for general paper summary, repo scanning, environment setup, command execution, title-only paper lookup, or replacing README guidance by default.
repo-intake-and-plan
lllllllama/rigorpilot-skills
Rigor Intake helper for README-first deep learning repo reproduction. Use when the task is specifically to scan a repository, read the README and common project files, extract documented commands, classify inference, evaluation, and training candidates, and return the smallest trustworthy reproduction plan to the main orchestrator. Do not use for environment setup, asset download, command execution, final reporting, paper lookup, or end-to-end orchestration.
minimal-run-and-audit
lllllllama/rigorpilot-skills
Rigor Run skill for README-first deep learning repo reproduction. Use when the task is specifically to capture or normalize evidence from the selected smoke test or documented inference or evaluation command and write standardized `repro_outputs/` files, including patch notes when repository files changed. Do not use for training execution, initial repo intake, generic environment setup, paper lookup, target selection, hidden scientific-meaning changes, or end-to-end orchestration by itself.

