mcpbeat Sign in

Fix Bp Docs Skill for Claude

'Audit and fix best practices docs for stale references, duplicates, obsolete docs, audit bp docs.'

1k tokens
context cost
the whole folder, loaded on every use
1
files
instructions only
0
copies elsewhere
how many repositories repackaged it
3472
stars on the repo
on the repository, not the skill itself

Install

one command, takes just this skill from the repository
npx skills add https://github.com/brave/brave-core --skill fix-bp-docs

What it tells the agent to use

found in the instruction text
Bash runs shell commands — read the instruction before connecting
Glob reads your files

The instruction itself

13 sections, as written by the author

Fix Best Practices Docs

Audit all best practices documentation files for issues and fix them. This skill

must be run from the brave-core directory.


Step 1: Paths

This skill runs from the brave-core (src/brave) directory. Best practices docs

are at ./docs/best-practices/ and the index is at ./docs/best_practices.md.

Set DOCS_DIR="./docs/best-practices".


Step 2: Read All Best Practice Files

Read docs/best_practices.md and every file in $DOCS_DIR/*.md to understand

the full set of docs.


Step 3: Check for Duplicates

Scan across all docs for rules that cover the same topic. Look for:

  • Rules with identical or near-identical bold principle statements
  • Rules with overlapping code examples covering the same pattern
  • Rules that were accidentally added to multiple category files

When a duplicate is found, keep the version in the more appropriate category

file and remove the other. Preserve all anchor IDs on the kept version so

existing links don't break.

Do NOT create reference-only stubs that just point to another rule. Either keep

the full rule or remove it entirely.


Step 4: Check for Stale Brave File References

Extract all brave/... file paths from code examples and verify they exist in

src/brave/. For each missing file:

  • Search for the renamed/moved file using find or Glob
  • Update the reference to the correct current path
  • If the file was deleted entirely and no replacement exists, update the

example to use a file that does exist

Skip paths that are obviously placeholder/illustrative (e.g.,

brave/components/my_feature/my_header.h,

brave/chromium_src/path/to/override.h).


Step 5: Check for Stale Chromium File References

Extract Chromium file paths (e.g., components/omnibox/browser/...,

chrome/browser/ui/...) from code examples and verify they exist in src/. For

each missing file:

  • Search for the renamed/moved file
  • Update the reference

Skip paths that are obviously placeholder/illustrative.


Step 6: Check for Stale Chromium Symbols

Look for references to specific Chromium class names, method names, and other

symbols in code examples. Verify they still exist in the Chromium source

(src/). Update any that were renamed.


Step 7: Check for Stale Brave Symbols

Look for references to specific Brave class names, method names, and other

symbols in code examples. Verify they still exist in src/brave/. Update any

that were renamed or removed.


Step 8: Check for Broken Internal References

Look for:

  • Links to other docs or files that don't exist (e.g.,

../testing-requirements.md)

  • References to anchor IDs that don't exist in the target file
  • Links to external URLs that are clearly wrong (but don't fetch them)

Step 9: Check for Formatting Issues

Look for:

  • Missing --- separators between rules
  • Missing anchor IDs (<a id="...">)
  • Duplicate --- separators
  • Inconsistent heading levels

Step 10: Check the Index

Verify docs/best_practices.md:

  • All listed docs exist
  • No doc is listed twice
  • All docs in $DOCS_DIR/ are represented in the index

Step 11: Report and Fix

For each issue found:

  • Describe the issue clearly
  • Fix it directly using Edit
  • Move on to the next issue

After all fixes, run ID validation:

python3 ./script/manage-bp-ids.py --validate

Important Guidelines

  • No Claude Code attribution in commits or PRs
  • Never remove anchor IDs even when removing duplicate rules — move them to

the kept version

  • Never create reference-only stubs that just point to another rule
  • Preserve the style of each document when making edits
  • Keep examples realistic — when updating a stale file path, pick a real

file that makes sense in context

  • When a code example uses a placeholder path (like path/to/foo.h), leave it

alone

Other skills for the same job

different authors, same section of the catalogue
Protocolsio Integration
by christophacham
×4

Integration with protocols.io API for managing scientific protocols. This skill should be used when working with protocols.io to search, create, update, or publish protocols; manage protocol steps and materials; handle discussions and comments; organize workspaces; upload and manage files; or integrate protocols.io functionality into workflows. Applicable for protocol discovery, collaborative protocol development, experiment tracking, lab protocol management, and scientific documentation.

16k tokens
Tailored Resume Generator
by frostant
×4

Analyzes job descriptions and generates tailored resumes that highlight relevant experience, skills, and achievements to maximize interview chances

3k tokens
Excalidraw Diagram Generator
by github
vendor ×3

Generate Excalidraw diagrams from natural language descriptions. Use when asked to "create a diagram", "make a flowchart", "visualize a process", "draw a system architecture", "create a mind map", or "generate an Excalidraw file". Supports flowcharts, relationship diagrams, mind maps, and system architecture diagrams. Outputs .excalidraw JSON files that can be opened directly in Excalidraw.

36k tokens scripts
Expo Dev Client
by openai
vendor ×3

Build and distribute Expo development clients locally or via TestFlight

961 tokens
Executing Plans
by ZhanlinCui
×3

Use when you have a written implementation plan to execute in a separate session with review checkpoints

542 tokens
Anndata
by christophacham
×3

Data structure for annotated matrices in single-cell analysis. Use when working with .h5ad files or integrating with the scverse ecosystem. This is the data format skill—for analysis workflows use scanpy; for probabilistic models use scvi-tools; for population-scale queries use cellxgene-census.

16k tokens
Benchling Integration
by christophacham
×3

Benchling R&D platform integration. Access registry (DNA, proteins), inventory, ELN entries, workflows via API, build Benchling Apps, query Data Warehouse, for lab data management automation.

14k tokens
Biopython
by christophacham
×3

Comprehensive molecular biology toolkit. Use for sequence manipulation, file parsing (FASTA/GenBank/PDB), phylogenetics, and programmatic NCBI/PubMed access (Bio.Entrez). Best for batch processing, custom bioinformatics pipelines, BLAST automation. For quick lookups use gget; for multi-service integration use bioservices.

24k tokens

How to use it

Copy the folder

Take brave/fix-bp-docs from the repository into ~/.claude/skills for personal use, or into .claude/skills inside a project.

Check the name does not clash

The agent identifies a skill by the name field in its header. Two skills with the same name cannot sit side by side — one of them will be ignored.