Chalk Labs
Need help deploying fix-checks?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/farhan-fix-checks
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: testing, devops
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/fix-checks
Tools it pre-approves 32
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Bash(ghprview:*),list:*),checks:*),diff:*),api:*),Bash(gitcheckout:*),fetch:*),pull:*),log:*),
Show 20 more
status:*),add:*),commit:*),push:*),branch:*),rev-parse:*),Bash(find:*),Bash(ls:*),Bash(python:*),Bash(python3:*),Bash(pip:*),Bash(pip3:*),Bash(uv:*),Bash(npm:*),Bash(yarn:*),Bash(pnpm:*),Bash(node:*),Bash(make:*),Bash(pytest:*),Bash(tox:*)
What's inside
- Skill name
fix-checks- Description
- Run ONLY when the user explicitly says "fix-checks". Finds the PR (asks if not given), checks out the branch locally, sets up a test environment, reproduces failing CI checks, fixes them in a loop until all pass, cleans up the fix, and pushes a proper commit.
- License
- unknown
- Allowed tools
- Bash(gh, pr, view:*),, Bash(gh, pr, list:*),, Bash(gh, pr, checks:*),, Bash(gh, pr, diff:*),, Bash(gh, api:*),, Bash(git, checkout:*),, Bash(git, fetch:*),, Bash(git, pull:*),, Bash(git, log:*),, Bash(git, diff:*),, Bash(git, status:*),, Bash(git, add:*),, Bash(git, commit:*),, Bash(git, push:*),, Bash(git, branch:*),, Bash(git, rev-parse:*),, Bash(find:*),, Bash(ls:*),, Bash(python:*),, Bash(python3:*),, Bash(pip:*),, Bash(pip3:*),, Bash(uv:*),, Bash(npm:*),, Bash(yarn:*),, Bash(pnpm:*),, Bash(node:*),, Bash(make:*),, Bash(pytest:*),, Bash(tox:*)
- Instructions
- 335 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from farhan/farhan-agent-skills
- 0.559score
draft-pr-comments
farhan
Draft PR review comments from review notes, a comment, or file content.
SkillAFreshness: AClaude Code +9 - 0.556score
create-stories
farhan
Break a client task description into well-scoped GitHub parent + sub-task issues, present an iterable plan for approval, then create and link them.
SkillAFreshness: AClaude Code +9 - 0.553score
review-code-commit
farhan
Review uncommitted git changes for bugs, typos, correctness issues, and security concerns before committing
SkillAFreshness: AClaude Code +9 - 0.552score
address-copilot-change-requests
farhan
Address GitHub Copilot change requests on a PR.
SkillAFreshness: AClaude Code +9 - 0.551score
pr-details
farhan
Generate the implementation details section for a PR description in a fixed why-then-what style.
SkillAFreshness: AClaude Code +9 - 0.550score
feanil-modernize-repo-skill
farhan
Reviewer's playbook for the Python-modernization class of Open edX PRs (uv + pyproject.toml + python-semantic-release, epic public-engineering#506).
SkillAFreshness: AClaude Code +9 - 0.546score
modernize-python-repos
farhan
Modernize an Open edX Python repo to use uv, pyproject.toml (PEP 621/735), optional src/ layout (if publishing to PyPI), and python-semantic-release.
SkillAFreshness: AClaude Code +9 - 0.534score
review-pr
farhan
This skill should be used when the user says "review PR", "review pull request", "start PR review", "I'm reviewing a PR", "let's review a PR", or starts a…
SkillAFreshness: AClaude Code +9 - 0.467score
content-guide
farhan
Guide for generating English content (not code) that follows minimal-wording, hyperlinked, and clean-spacing conventions.
SkillCFreshness: CClaude Code - 0.301score
commit-guide
farhan
No description from the publisher yet.
SkillAFreshness: AClaude Code +9 - 0.298score
create-test-problem-block
farhan
No description from the publisher yet.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 27, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/farhan/farhan-agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from farhan
- 0.559score
draft-pr-comments
farhan
Draft PR review comments from review notes, a comment, or file content.
SkillAFreshness: AClaude Code +9 - 0.556score
create-stories
farhan
Break a client task description into well-scoped GitHub parent + sub-task issues, present an iterable plan for approval, then create and link them.
SkillAFreshness: AClaude Code +9 - 0.553score
review-code-commit
farhan
Review uncommitted git changes for bugs, typos, correctness issues, and security concerns before committing
SkillAFreshness: AClaude Code +9 - 0.552score
address-copilot-change-requests
farhan
Address GitHub Copilot change requests on a PR.
SkillAFreshness: AClaude Code +9 - 0.551score
pr-details
farhan
Generate the implementation details section for a PR description in a fixed why-then-what style.
SkillAFreshness: AClaude Code +9 - 0.550score
feanil-modernize-repo-skill
farhan
Reviewer's playbook for the Python-modernization class of Open edX PRs (uv + pyproject.toml + python-semantic-release, epic public-engineering#506).
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get fix-checks running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
fix-checks skill. Agent Mart. https://agentmart.dev/skills/farhan-fix-checks (last updated 2026-10-24)