speq-skill

Audit a speq project's health — spec-library structure, feature/decision-log/plan validation, mission-to-spec sync, unrecorded plans, and gitignore hygiene — then guide fixes. Use when the user asks to audit, health-check, doctor, lint, or sanity-check the specs or repo, or after cloning or inheriting a speq project.

Code review tag taxonomy and findings output format — guardrail violations, dead code, obsolete tests, bad comments, optimizations, YAGNI/over-engineering. Triggered by code-reviewer.

Headless follow-up to speq-plan-pr. Continues on a plan's feat/plan-name branch, runs speq-implement, bumps the version, runs the real test suites, records only if green, then pushes and opens/updates a PR. Arg: plan name, PR number, or branch name.

Orchestrate implementation of reviewed plans according to the spec deltas. Arg: <plan-name>.

Create specs/mission.md via interactive interview. Detects brownfield vs greenfield.

Headless, non-interactive version of speq-plan. Plans a feature without a live interview, commits the result to a feat/plan-name branch, and opens a PR. If a decision genuinely needs a human, it persists the partial plan and open questions and asks in a PR comment instead of blocking. Arg — plan name, feature intent text, PR number, or branch name.

Adversarial plan-review method and challenge taxonomy — premortem framing, 14-tag/5-axis taxonomy, severity discipline, and findings output format. Triggered by plan-reviewer.

Plan and create spec deltas for new features or changes to existing features.

Merge implemented spec deltas into permanent specs library.

The git/gh operation-to-command mapping and return formats for git-agent — the sole write-permitted actor in this system. Triggered by git-agent.

Plan-authoring workflow — spec delta authoring, test mapping, plan.md/decision-log.md generation, expert-task tagging, headless escalation, and revision mode. Triggered by planner-agent.

Delta-merge procedure — DELTA marker semantics, library-organization thresholds, and ADR-promotion field mapping. Triggered by recorder-agent.

Prose guardrails for speq artifacts and GitHub PRs, issues, and comments — front-loaded (BLUF), terse, unambiguous writing anchored in established style and requirements standards. Triggered by speq prose-authoring skills and agents.

TDD and code quality guardrails triggered by speq-implement.

Query specs via speq CLI. Search scenarios, list features, validate structure.

Semantic code navigation and editing triggered by speq-skills.

Search for external documentation and research triggered by speq-skills.

Enforce Git discipline for speq-skills.