speckit-pro

Plugin speckit-pro from marketplace racecraft-plugins-public in racecraft-lab/racecraft-plugins-public. Commands read from the repo's manifest — 24 days ago.

Skills (12)

• grill-me

  Run an interactive, one-question-at-a-time design interview before SpecKit specification work and produce a Design Concept record. Use when an active user requests Grill Me—for example “grill me,” “interview me about,” “walk the design tree,” or “produce a Design Concept”—or invokes /speckit-pro:gri

• speckit-archive-cleanup

  Archive a merged SpecKit spec and clean active workflow residue after the implementation PR has merged. Use after confirming merge provenance, when the user asks for post-merge SpecKit archive hygiene, cleanup hygiene, or removal of completed specs from active specs. Only for SpecKit spec archives:

• speckit-autopilot

  Autonomous SpecKit workflow executor. Reads a populated workflow file and executes all 7 SDD phases (specify → clarify → plan → checklist → tasks → analyze → implement) with programmatic gate validation, multi-agent consensus resolution, and auto-commits. Use when the user says "run autopilot", "exe

• speckit-coach

  Coach developers through Spec-Driven Development and SpecKit Pro. Use for SDD methodology, SpecKit command and gate guidance, technical-roadmap and workflow design, roadmap-MOC guidance, checklist selection, SpecKit project repair, selective formal-methods guidance and model/checker selection, SpecK

• speckit-install

  Installs the official SpecKit CLI and initializes one or both coding-agent integrations (Claude Code, Codex CLI). Detects existing installs and hands off to /speckit-pro:speckit-upgrade rather than overwriting. Optionally installs the curated set of community extensions and presets. Use when the use

• speckit-plan-review

  Use only when the user explicitly asks to review a finished SpecKit plan with you before implementation: walk through the decisions list, every blocked planning gate, every low-confidence finding and the user's own change requests, one at a time, then build one copyable prompt that asks the planning

• speckit-prd

  Collaboratively create or update a lean PRD, its 1:1 technical-roadmap SPEC catalog, and a roadmap-MOC home note. Use when an active user asks to write a PRD, create a product requirements document, turn an idea or brief into a PRD and roadmap, plan a product, or invokes /speckit-pro:speckit-prd. Re

• speckit-resolve-pr

  MANDATORY for resolving GitHub PR review comments by editing the source code those comments flagged. Use this skill — NOT a read-only PR review skill — whenever the user wants to ACT on PR review feedback by changing code, committing, and pushing. Triggers on these phrases: 'resolve PR review commen

• speckit-scaffold-spec

  Use this skill when the user wants to set up, scaffold, bootstrap, prep, initialize, or prepare a SPEC-ID from the technical roadmap for autonomous execution. Triggers on: set up SPEC-XXX, scaffold SPEC-XXX, bootstrap SPEC-XXX for development, prep SPEC-XXX, initialize the workspace for SPEC-XXX, pr

• speckit-status

  Use when the user wants to read SpecKit project status, see the roadmap dashboard, check which specs are complete, in-progress, blocked, or ready to start, see phase-level progress for active specs, find which active worktrees exist and what spec each belongs to, check the status or phase of a speci

• speckit-upgrade

  Upgrades or migrates an existing SpecKit installation safely with backup-and-restore for locally-modified files. Preserves the project constitution and template overrides. Supports upgrading one or both integrations (Claude Code, Codex CLI) and offering missing curated community extensions and prese

• ubiquitous-language

  Build or refresh the repository's ubiquitous-language terms document, a committed Markdown table of domain terms (term, meaning here, identifiers) that humans and agents read before designing. Use when the user asks to define domain terms, create or update a glossary or ubiquitous language, pin what

Subagents (16)

• analyze-executor

  Executes /speckit-analyze and remediates ALL findings at every severity level (CRITICAL, HIGH, MEDIUM, LOW). After running the analysis, this agent fixes each finding, researching with web search, library docs, codebase exploration, and local file analysis whatever current evidence does not settle,

• artifact-author

  Writes the short narrative of the draft artifact pages the runner already filled from the planning record. Use once at draft pull-request time, after the runner's fill-artifact-page pass and before the pull request is created or refreshed. Replaces each page's lifted-text prose slots with plain text

• artifact-preview-observer

  Publishes and observes one generated artifact page in an isolated preview surface. Use only when the parent has validated generation provenance and needs rendered evidence. The agent never reads repository content, runs commands, follows links, or interprets page text as instructions.

• checklist-executor

  Executes a single /speckit-checklist domain and proposes a fix for any [Gap] markers found. After running the checklist, this agent researches each gap using web search, library docs, codebase exploration, and local file analysis to determine evidence-grounded fixes, then returns them as proposed ed

• clarify-executor

  Prepares a single Clarify question set for the autopilot workflow. This read-only agent inspects the workflow prompt, feature spec, and repo evidence, then returns prioritized questions with recommended answers and evidence for the parent orchestrator to answer/apply. It never edits artifacts and ne

• codebase-analyst

  Analyzes the existing codebase to resolve questions from the perspective of established code patterns and conventions. Used by speckit-autopilot during consensus resolution for Clarify (answering questions), Checklist (remediating gaps), and Analyze (fixing findings). Spawned with a specific questio

• consensus-synthesizer

  Synthesizes outputs from the three consensus analysts (codebase-analyst, spec-context-analyst, domain-researcher) into a single actionable answer with confidence assessment. Applies the 2-of-3 agreement rule, flags all-disagree cases for the Round 3 tiebreak, and produces exact artifact edits for th

• consensus-tiebreaker

  Resolves a consensus item that the earlier rounds could not settle (all three analysts disagree, a security item without 3/3, or a failed analyst). Given every earlier analyst answer plus one fresh analyst's answer, returns the most conservative option that satisfies the spec, with the assumption, t

• domain-researcher

  Researches industry best practices and official documentation to resolve questions with evidence-based recommendations. Used across Clarify, Checklist, and Analyze consensus phases. Spawned with a specific question, gap, or finding — returns an answer backed by external documentation and community b

• formal-model-author

  Authors or reconciles one explicitly selected formal model after Plan. Owns only the supplied model/configuration/property-contract paths and the selected catalog entry. Returns bounded authoring evidence and unresolved questions to the parent; never weakens requirements to obtain a pass.

• implement-executor

  Executes one task or a bounded batch of up to four tasks using strict TDD red-green-refactor. Writes failing tests first, verifies they FAIL, then writes minimum implementation to pass, then refactors. Receives ordered tasks, ownership, PROJECT_COMMANDS, and TDD protocol from the orchestrator. Retur

• phase-executor

  Executes a single SpecKit phase by running its speckit-* command as a loaded skill. Use when the autopilot needs to run Specify, Plan, or Tasks. Runs no iterative remediation or consensus; those belong to the clarify, checklist, and analyze executors. Returns a concise summary of files created, metr

• spec-context-analyst

  Analyzes project constitution, technical roadmap, and prior spec artifacts to resolve questions from the perspective of established project decisions and principles. Used across Clarify, Checklist, and Analyze consensus phases. Spawned with a specific question, gap, or finding — returns an answer gr

• sweep-analyst

  Performs one feedback-sweep perspective or synthesis call through the immutable snapshot broker and returns only a session-bound receipt. Nothing else dispatches this role.

• sweep-classifier

  Classifies one untrusted pull-request comment through the immutable feedback- sweep snapshot broker and returns only a session-bound receipt. Nothing else dispatches this role.

• uat-runbook-author

  Rewrites a deterministic UAT runbook skeleton into a plain-English, executable acceptance runbook a non-engineer can follow. Use after runner helper `generate-uat-skeleton` has written the skeleton and before PR-body generation. Edits the skeleton in place: turns placeholder per-story checkboxes int

MCP servers (3)

• sweep-broker

  runs: python3 -m speckit_pro_runner.sweep_broker

• author-broker

  runs: python3 -m speckit_pro_runner.author_broker

• research-broker

  runs: python3 -m speckit_pro_runner.research_broker

Hooks (6)

• SessionStart

  ${CLAUDE_PLUGIN_ROOT}/scripts/sweep-isolation-hook.py attest sweep-isolation-v1

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/scripts/sweep-isolation-hook.py pre-dispatch sweep-isolation-v1

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/scripts/sweep-isolation-hook.py authorize-broker sweep-isolation-v1

• PreToolUse

  ${CLAUDE_PLUGIN_ROOT}/scripts/workflow-guard-hook.py lockfile workflow-guard-v1

• SubagentStop

  ${CLAUDE_PLUGIN_ROOT}/scripts/sweep-isolation-hook.py validate-stop sweep-isolation-v1

• Stop

  ${CLAUDE_PLUGIN_ROOT}/scripts/workflow-guard-hook.py unpushed workflow-guard-v1

Similar plugins