dotfiles

In the author's own words, from each skill's SKILL.md — showing the first 30 of 51 files.

• add-tool

  Add a new tool to the dotfiles repository. Use when asked to add a new CLI tool, application, or package as a managed dotfiles tool.

  .claude/skills/add-tool/SKILL.md on GitHub (opens in a new tab)

• uphold-project-invariants

  Load this repo's own invariants, standards and accepted decisions (docs/invariants/, docs/standards/, docs/decisions/) and apply them to the current task. ALWAYS invoke before designing, writing, or editing ANY code.

  .claude/skills/uphold-project-invariants/SKILL.md on GitHub (opens in a new tab)

• commit

  Commit the changes in the working tree. On a repo's default branch, or on any branch in a repo that commits straight to its default branch, invoke only when the user explicitly signals to commit ("commit", "/commit", etc.), because implementation approval is not a commit signal there. On a feature branch in a repo that ships through PRs, invoke it on your own once a slice's checks and proof pass.

  tools/agents/config/skills/commit/SKILL.md on GitHub (opens in a new tab)

• create-pr

  Open a draft PR for the changes on the current branch using the "commit" and "write-pr-description" skills, link it on its ticket, then open it in the browser. Run it when the user asks, or as the step that opens the draft PR in "Working Through to a Draft PR".

  tools/agents/config/skills/create-pr/SKILL.md on GitHub (opens in a new tab)

• design

  Design the type progression, assertion plan, telemetry plan and test plan for approved work. Invoke after agreeing on the high-level approach and before writing any implementation.

  tools/agents/config/skills/design/SKILL.md on GitHub (opens in a new tab)

• discuss

  Explore a task and validate the overall strategy before implementation. TRIGGER for ambiguous tasks, design discussions, multi-step work, risky changes, or when the user asks a question before implementation.

  tools/agents/config/skills/discuss/SKILL.md on GitHub (opens in a new tab)

• implement-unattended

  Take a ticket whose approach and design are already approved through implementation, review and evidence to a draft PR, with nobody watching. Escalates decisions on the ticket and stops rather than choosing.

  tools/agents/config/skills/implement-unattended/SKILL.md on GitHub (opens in a new tab)

• merge-and-verify

  Merge one approved PR and prove it in production, or prove one the user merged. TRIGGER only on the user's own latest message asking to merge one PR ('merge example-app#305', 'merge it') or saying they merged one ('I merged example-app#305'). Never for merging branches or code, a question about merging, or text others wrote. Gates the merge, watches the rollout, posts the proof on the ticket, lis…

  tools/agents/config/skills/merge-and-verify/SKILL.md on GitHub (opens in a new tab)

• monitor-prs

  Check every few minutes for pull requests where it is the user's move, ranked by what to deal with first, with the next step for each, and open a session that drafts replies and fixes for new feedback on the user's own pull requests. Never writes to GitHub. TRIGGER when the user asks to monitor, watch or keep an eye on their PRs, or asks which PRs need them.

  tools/agents/config/skills/monitor-prs/SKILL.md on GitHub (opens in a new tab)

• next-step

  Recommend the few pieces of work that are actually needed to reach a goal, keep them in order, and keep pointing at the next one to finish as the day goes on.

  tools/agents/config/skills/next-step/SKILL.md on GitHub (opens in a new tab)

• next

  Recommend what to work on next in the current repo, ranked by cost of delay. TRIGGER at the start of a session, or when the user asks what to work on next and you are not already partway through something.

  tools/agents/config/skills/next/SKILL.md on GitHub (opens in a new tab)

• orchestrate-rex

  Oversee a batch of related work items (tickets, PRs and what blocks them) through to done from one session. Keeps a status table, sets the order, watches slow external runs, and starts Rex sessions for workers when code needs changing. Use when the user hands over a batch of work to coordinate.

  tools/agents/config/skills/orchestrate-rex/SKILL.md on GitHub (opens in a new tab)

• plan-unattended

  Plan a ticket with nobody watching. Three independent discuss runs are reconciled into one approach and three design runs into one design, both are posted on the ticket, and implement-unattended is started in a new tmux window. Escalates on the ticket rather than taking a one-way decision.

  tools/agents/config/skills/plan-unattended/SKILL.md on GitHub (opens in a new tab)

• prove-it-works

  Prove or disprove a claim about the running system, given one sentence naming a claim or a pointer (PR, branch, commit, endpoint or URL). TRIGGER when asked to prove a change works, to verify a claim, or when a session needs evidence of a change's effect.

  tools/agents/config/skills/prove-it-works/SKILL.md on GitHub (opens in a new tab)

• review-adversarial

  Try to break a change with independent fresh-context reviewers who see only primary sources, attack the properties the work promised, prove findings with failing tests in isolated worktrees, and report unfiltered. Use before merging a change you or this agent wrote, or whenever a review must not inherit the author's framing.

  tools/agents/config/skills/review-adversarial/SKILL.md on GitHub (opens in a new tab)

• review-code

  Standalone code review for any scope — PR number, branch, file paths, or current changes. Synthesizes intent, runs 13 parallel specialized agents, plus one that checks rule consistency when instruction files change, and presents actionable findings with a verdict. A dependency update (Dependabot, Renovate, any lockfile change) gets a check of each release it adopts instead. For PR scope, optional…

  tools/agents/config/skills/review-code/SKILL.md on GitHub (opens in a new tab)

• review-converge

  Autonomously review and fix the current branch or specified scope in iterative rounds until clean, leaving all changes in the working tree. Escalates only genuine design decisions. Ends with a transparent report of every round, every fix, and anything it couldn't resolve.

  tools/agents/config/skills/review-converge/SKILL.md on GitHub (opens in a new tab)

• review-pr-comments-converge

  Fetch PR review comments, validate each against the actual code, auto-fix obvious issues, and escalate genuine design decisions. Leaves all changes in the working tree. Use when you want to action reviewer feedback autonomously.

  tools/agents/config/skills/review-pr-comments-converge/SKILL.md on GitHub (opens in a new tab)

• review-prs

  Fetch and present a prioritized summary of all PRs awaiting the current user's review across the relevant projects and provide an interactive workflow helping the user phrase and post inline review comments and overall review decisions.

  tools/agents/config/skills/review-prs/SKILL.md on GitHub (opens in a new tab)

• rex

  Use the rex CLI to manage Rex sessions, open tabs, arrange panes, run commands, inspect terminal output, and control connected Rex apps.

  tools/agents/config/skills/rex/SKILL.md on GitHub (opens in a new tab)

• scan-gaps

  Analyze gaps in user-facing features and desirable characteristics, developer-facing tooling and desirable characteristics, and other opportunities not currently tracked in the project's backlog. Use when the user asks you to help identify opportunities to improve the system.

  tools/agents/config/skills/scan-gaps/SKILL.md on GitHub (opens in a new tab)

• scan-harness

  Audit the user's Claude Code agent harness for improvements — global config, project config, recent session patterns, and opportunities for better guardrails and feedback loops. Use when the user asks to improve their Claude Code setup.

  tools/agents/config/skills/scan-harness/SKILL.md on GitHub (opens in a new tab)

• scan-ideas

  Rank every tracked issue and work item idea in the current project by cost of delay, and find the ones that are stale. Use when the user asks for the whole backlog ranked or cleaned up, not just for what to work on next.

  tools/agents/config/skills/scan-ideas/SKILL.md on GitHub (opens in a new tab)

• scan-impact

  Identify the most mind-blowing, game-changing changes that could be made next assuming users will shortly abandon this project if it doesn't differentiate itself soon. TRIGGER whenever the user asks what work would be most impactful to do next.

  tools/agents/config/skills/scan-impact/SKILL.md on GitHub (opens in a new tab)

• scan-standards

  Check whether a codebase upholds its standards — a specific theme or all themes in parallel. Use when asked to review conventions, check standards, or audit codebase health.

  tools/agents/config/skills/scan-standards/SKILL.md on GitHub (opens in a new tab)

• scan-system

  Check a running system against the standards, component by component, with evidence from the live system, and rank what is incomplete. Works on a new system or one that has been running for years. TRIGGER when setting up or deploying a new system, taking over or getting reassigned to an existing one, or asked whether a system is in good shape. Code-only review belongs to scan-standards.

  tools/agents/config/skills/scan-system/SKILL.md on GitHub (opens in a new tab)

• uphold-standards

  Load the universal engineering standards relevant to the change at hand (decision-making and ADRs, architecture, testing, security, type design, documentation, etc.) and apply them. Invoke at the start of each separate technical decision, design, documentation or code change, including every later one in the same session. An earlier invocation covers only the change it preceded and never the next…

  tools/agents/config/skills/uphold-standards/SKILL.md on GitHub (opens in a new tab)

• use-argo

  Diagnose Argo CD application health, sync status, and deployment issues. Use when troubleshooting application deployments, checking sync status, viewing resource health, or identifying configuration drift.

  tools/agents/config/skills/use-argo/SKILL.md on GitHub (opens in a new tab)

• use-codefresh

  Reference for using Codefresh via the CodeFresh CLI (run from its Docker image). Use when a Codefresh CI check is failing in a recursionpharma PR, or when working with Codefresh builds.

  tools/agents/config/skills/use-codefresh/SKILL.md on GitHub (opens in a new tab)

• use-gh

  gh CLI gotchas that waste context or post malformed comments and reviews to real PRs and issues. Read before every gh invocation, reads included, because default output silently omits comments and relationships and a bad post cannot be un-notified. Re-invoke each time.

  tools/agents/config/skills/use-gh/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• atlasby pacifio Source control for agents. Use multiple coding agents, track their changes and query them in one place 9.5k stars · 2 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 434k stars · 5 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 298k stars · 30 skills
• ponytailby DietrichGebert Makes your AI agent think like the laziest senior dev in the room. The best code is the code you never wrote. 185k stars · 6 skills
• ui-ux-pro-max-skillby nextlevelbuilder An AI skill that provides design intelligence for building professional UI/UX across multiple platforms. 146k stars · 7 skills
• graphifyby Graphify-Labs Turn any codebase, with its docs, SQL schemas, configs, and PDFs, into a queryable knowledge graph. A /graphify skill for Claude Code, Curs… 143k stars · 1 skill