codagent

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.

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".

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".

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".

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").

Autonomous implementer agent that executes a single task end-to-end using TDD 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".

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".

Enforces test-driven development for feature work, bug fixes, and refactoring, activating for requests such as "implement", "fix", "add feature", "write tests first", or "TDD".

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".

Creates a structured implementation task breakdown for a structured change, synthesizing proposal, design, and specs into self-contained per-task files. Use when the tasks artifact is the next step in a change.

Adversarial review of a proposal — challenges the why, what, and how, and suggests alternative approaches. Use when the user says "review proposal", "challenge this proposal", "adversarial review", "poke holes", "stress test the proposal", or wants a second opinion on a proposal before moving to specs/design.

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.

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".

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.

Reviews design artifacts (proposal, specs, design, tasks) for internal consistency, gaps, and cross-artifact alignment. Use when the user says "review spec", "review artifacts", "review the design docs", "review the change", or wants a quality check on proposal, spec, design, or task files before implementation.

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.

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 OpenSpec 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.

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

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.

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".