agent-skills

In the author's own words, from each skill's SKILL.md.

• ask-questions

  How to ask users questions interactively: which tool to use, how to batch questions, and when to ask serially. Follow this skill when asking clarifying questions, requesting confirmation, collecting missing requirements, or pausing for user input. Invoked by other skills rather than directly by the user.

  skills/ask-questions/SKILL.md on GitHub (opens in a new tab)

• call-agent

  Safely invokes one Runner-owned child agent with a complete standalone prompt, independently verifies its findings, and reports results without hiding failures or disagreements. Use when a workflow or caller asks to use codagent:call-agent, call the Runner-owned call_agent tool, obtain an independent agent review, or delegate one bounded task to an Agent Runner profile or declared named session.

  skills/call-agent/SKILL.md on GitHub (opens in a new tab)

• design

  Creates design artifacts through collaborative brainstorming of approaches, architecture, and trade-offs. Use when the user says "design this", "create a design", "brainstorm approaches", or "write a design doc".

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

• finalize-pr

  Orchestrates the full post-implementation loop: push PR → wait for CI → fix failures → repeat until CI passes or termination rules trigger a pause. This skill should be used when the user says "ship it", "finalize pr", "push and fix CI", "push pr and wait for CI", or invokes "codagent:finalize-pr".

  skills/finalize-pr/SKILL.md on GitHub (opens in a new tab)

• fix-pr

  Fixes CI failures and review comments on the current branch's pull request by dispatching a fixer subagent, verifying with the validator, and pushing the fix. Use when the user says "fix pr", "fix CI failures", "address review comments", or invokes "codagent:fix-pr".

  skills/fix-pr/SKILL.md on GitHub (opens in a new tab)

• handoff

  Summarizes a specific aspect of the current conversation so another agent can resume. Use when the user says "handoff", "summarize for handoff", "write a handoff", or wants to capture context for another agent session. The user MUST specify what aspect to summarize in their prompt (e.g., "handoff the debugging progress", "handoff the design decisions").

  skills/handoff/SKILL.md on GitHub (opens in a new tab)

• implement-and-validate

  Autonomous implementer agent that executes a single task end-to-end and verifies with Agent Validator. Activates for requests such as "implement this task", "finish this ticket", "apply this spec end-to-end", or "complete the implementation".

  skills/implement-and-validate/SKILL.md on GitHub (opens in a new tab)

• implement-change

  Autonomous tech lead that implements a full change end-to-end by dispatching one subagent per task sequentially using implement-and-validate, running the validator, and finalizing the PR. Activates for requests like "implement this change", "apply the change", "ship it", or "execute the tasks".

  skills/implement-change/SKILL.md on GitHub (opens in a new tab)

• init

  Initializes Agent Skills in a project by checking prerequisites and verifying the validator configuration. Use when the user says "init", "set up agent-skills", or "initialize agent-skills".

  skills/init/SKILL.md on GitHub (opens in a new tab)

• plan-tasks

  Creates a structured implementation task breakdown for a structured change, synthesizing proposal, design, specs, and any supplied test-plan obligations into self-contained per-task files; use when the tasks artifact is the next step in a change.

  skills/plan-tasks/SKILL.md on GitHub (opens in a new tab)

• prepare-acceptance

  Explores an implemented change to find defects its green test suite missed, exercises every user-visible requirement the change adds or modifies at least once, sizes further exploration to what actually changed, reports findings without fixing them, waits for current-head CI, and prepares evidence for human review when preparing a change for acceptance, gathering review evidence, performing explo…

  skills/prepare-acceptance/SKILL.md on GitHub (opens in a new tab)

• proposal-review

  Adversarial review of a proposal — challenges the why, what, and how, and suggests concrete alternatives. Use when asked to review a proposal, challenge an idea, stress-test an approach, or provide a devil's advocate perspective before specs or design are written.

  skills/proposal-review/SKILL.md on GitHub (opens in a new tab)

• propose

  Evaluate whether a software idea is worth building, then write the proposal document. Use when the user wants to assess an idea, says "evaluate", "propose", "is this worth building", or "should we build". If the idea passes evaluation, write the proposal document using the provided template.

  skills/propose/SKILL.md on GitHub (opens in a new tab)

• push-pr

  Commits changes, pushes to remote, and creates or updates a pull request for the current branch. Use when the user says "push pr", "create pr", "push and create pr", or invokes "codagent:push-pr".

  skills/push-pr/SKILL.md on GitHub (opens in a new tab)

• review-approach

  Performs the final review of a completed proposal, product specification, technical design, and test plan for cross-artifact consistency, consequential gaps, missing decisions, weak tradeoffs, failure modes, testing strategy, and better alternatives; use when asked to review an approach, challenge design or testing decisions, find gaps in completed definition artifacts, or provide a second opinio…

  skills/review-approach/SKILL.md on GitHub (opens in a new tab)

• review-assumptions

  Reviews risky/notable assumptions and context gaps surfaced by implementor session reports, fixes high-confidence issues directly, and asks one clarifying question at a time for ambiguous findings. Use when the user says "review assumptions", "audit implementor assumptions", or when invoked by a workflow's assumption-review step.

  skills/review-assumptions/SKILL.md on GitHub (opens in a new tab)

• review-spec

  Reviews proposal, specification, design, and task artifacts for internal consistency, testability, traceability, and cross-artifact alignment. Use when asked to review a spec, review artifacts, check design documents, check a change for consistency, or verify artifact quality before implementation.

  skills/review-spec/SKILL.md on GitHub (opens in a new tab)

• review-tasks

  Reviews an implementation task plan against its approved proposal, specifications, design, and test plan, finding only defects that can be corrected in the task files; use when asked to review tasks, review an implementation plan, verify task and automated-test coverage, or check whether a task breakdown is ready for autonomous implementation.

  skills/review-tasks/SKILL.md on GitHub (opens in a new tab)

• session-report

  Audits your session for assumptions and context gaps — things only a human can act on. Use when the user says "session report", "review assumptions", "what did you struggle with", "audit your session", or wants a retrospective on execution quality.

  skills/session-report/SKILL.md on GitHub (opens in a new tab)

• simple-plan

  Lightweight planning for small, quick changes. Combines propose, spec, and (optionally) design into one conversational pass, then writes tasks.md so the change is ready for implementation. Activates when users ask for "simple plan", "quick plan", "plan this", or "planning mode" for a change that doesn't warrant the full propose/spec/design ceremony.

  skills/simple-plan/SKILL.md on GitHub (opens in a new tab)

• spec

  Drives interactive requirement discovery to produce spec files. Use when the user says "spec this", "write specs", "create specs", or "run the spec skill".

  skills/spec/SKILL.md on GitHub (opens in a new tab)

• task-compliance

  Review an implementation against task file requirements. Checks every spec scenario and Done When criterion, identifies gaps, and reports them. Use when the user says "task compliance", "check compliance", "review against the task", or to verify implementation completeness before shipping.

  skills/task-compliance/SKILL.md on GitHub (opens in a new tab)

• test-flows

  Exercises a small or branch-local software change through representative public user or client flows and reports concise observed evidence, defects, ambiguities, and limitations without fixing code, running automated suites, requiring a PR, or preparing formal acceptance; use for lightweight manual-style testing, smoke testing a completed change, or targeted verification after a small fix.

  skills/test-flows/SKILL.md on GitHub (opens in a new tab)

• test-plan

  Collaboratively creates a risk-based test plan for a defined software change using the automated test pyramid plus the envelope an exploratory acceptance pass runs under and exceptional human-only testing; use after specifications and design are complete, when asked to plan testing, define integration or end-to-end coverage, set testing authorizations, or create test-plan.md before implementation…

  skills/test-plan/SKILL.md on GitHub (opens in a new tab)

• wait-ci

  Polls CI check status for the current branch's pull request and reports pass/fail/pending/comments, surfacing PR review comments even when CI is green. Use when the user says "wait for CI", "check CI", "poll CI", or invokes "codagent:wait-ci".

  skills/wait-ci/SKILL.md on GitHub (opens in a new tab)

• release

  Creates a release PR from merged PRs — gathers merged PRs since last tag (plus any unmerged current-branch PR), calculates semver bump from conventional commit titles, generates changelog entries, and opens a release PR. Works from any branch: includes both main and current branch changes. Activates for requests such as "release", "cut a release", "create a release PR", "prepare a release", or "b…

  .agents/skills/release/SKILL.md on GitHub (opens in a new tab)

No skill matches that filter.

Similar skills

• superpowersby obra An agentic skills framework & software development methodology that works. 300k stars · 15 skills
• skillsby mattpocock Skills for Real Engineers. Straight from my .agents directory. 293k stars · 30 skills
• ECCby affaan-m The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Cod… 280k stars · 30 skills
• reaby morluto Reverse engineer anything with agents, from app behavior down to native binaries. 270k stars · 1 skill
• andrej-karpathy-skillsby multica-ai A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls. 220k stars · 1 skill
• skillsby anthropics Public repository for Agent Skills 181k stars · 19 skills