Skill Claude Code
Validate a completed wave against REQs assigned to that wave by the plan / WorkManifest, plus repo artifacts and cross-spec contracts. Produces a Ground Report (GF- findings) including Contracts Produced for next-wave pre-implement. Writes locally and emits Forge readiness — never commits or merges. Use after Pass-2…
Skill Claude Code
After the dev team has written their spec slice from the PRD, review it against the current codebase — baseline, gaps, impact, test harness, architecture governance (ADR + MDC), risks, and 4-lane triage. Writes the report locally and emits Forge readiness for the open Draft spec PR while Gate 2 remains spec-pending.…
Skill Claude Code
After human wave-acceptance / tip fixes on a wave PR, extract structured programme learning (SPEC / SKILL / HARNESS / ENV) with stable L- ids for Gateflow to persist and for ground-spec to cite. Closeout hop — does not write the Ground Report. Use Enter-at or /learning-extract after Pass-1 stop at wave-acceptance.
Skill Claude Code
Execute the per-wave implementation loop: implement against spec one TASK at a time, run checks/tests, fix failures, record local TASK proof — then stop for human wave-acceptance. Writes Wave-Execution artifact and one stage-level commitworkspace Forge package after the wave is green. Never commits/pushes. Use during…
Skill Claude Code
Before implementing one wave slice, produce a pre-flight checklist: verify the prior wave's human gate is satisfied, confirm contracts consumed from prior Ground Reports match what was actually built, then read specs/ADRs/rules. Gate-only — never opens a branch or implements product code. Use when starting a wave…
Skill Claude Code
Engineering-lane purge: after initiative-closure judgment, delete allowlisted app working papers for one initiative (feas, TDD, plan, per-wave reports, Draft ADRs). Refuse KEEP paths (product INIT, Accepted ADRs, source/tests/ verify scripts). Commit via Forge when pin requires it. No report file — success is handoff…
Skill Claude Code
Translate the PRD into a spec slice for this repo. Reads the PRD from the meta PRD PR branch or merged develop, extracts capabilities relevant to this repo, drafts docs/specification/product/INIT-.md locally, and produces a Draft-PR readiness handoff (handoff.forge for opendraftpr). Publish via /open-draft-pr or…
Skill Claude Code
After feasibility (and technical review when applicable), produce a wave-level implementation plan with REQ/TASK/FILE/TEST tables and a WorkManifest YAML seed section (§9). Runs while the spec PR is open, before spec merge. Board seeding (gh issue create) happens after spec PR merge — not before.
Skill Claude Code
After feasibility, produce a principal-engineer design document: resolve all engineering decisions (ADRs, interface contracts, test policy, module boundaries), draft any required ADRs, and route only true product questions back to PM on the meta PRD PR. Runs after /initiative-feasibility on both pass and findings (pin…
Skill Claude Code needs its repo
Phase 1 engg-reviews: ensure local Graphify code graphs are present and fresh for a fleet of candidate app repos at develop. Resolves candidates from an Impact-Map or PE list, syncs sibling clones, builds or updates graphify-out/, and records developsha + graphdigest. Gate-independent — never sets impact-map- or spec…
Skill Claude Code
Phase 1 engg-reviews (PE): after /prd-codebase-map, format product questions (scenario, example, recommendation, why, alternatives) and post them on the open Meta PRD PR with an explicit request for PM feedback. Does not decide product answers, does not edit the PRD, does not run PM skills. Gate- independent — never…
Skill Claude Code
Phase 1 engg-reviews: map an open meta PRD onto a fleet of app repos using as-built status plus in-depth codegraph evidence (Graphify query/path/explain). Produces PRD-Codebase-Map artifact and PM-facing product questions (scenario, example, recommendation, why). Gate-independent — does not require impact-map-lgtm and…
Skill Claude Code
Phase 1 engg-reviews (PE, optional): interactively walk product questions from a PRD-Codebase-Map. Lets a product-minded PE refine recommendations (scenario, stance, alternatives) before posting to the Meta PR. Writes PE-Product-Stance artifact — proposals only, not PM authority. Does not edit the PRD, does not set…
Skill Claude Code
Publish includable workspace changes to the remote head for this run (human walker Forge tooling). Use after a content skill when pin forge.commitworkspace is optional or required. Orchestrators use ForgeClient instead — do not auto-invoke this skill.
Skill Claude Code
After spec PR merge, seed the programme engineering board from Implementation Plan §9 WorkManifest: verify merge gate and board binding, present the EPIC/wave plan, then after explicit authorization create epic and wave issues. Human walker ForgeClient parity (createboardtickets). Orchestrators use BoardService /…
Skill Claude Code
Open or update a Draft pull request and apply projection labels from pin ⋉ handoff.forge (human walker). Use after content skills such as spec-draft, prd-impact-map, or pre-implement (wave Draft PR) when the user authorizes publish. Orchestrators use ForgeClient on external-action nodes instead — do not auto-invoke…
Skill Claude Code
Map a PRD to affected repos using the service catalog. Reads the PRD and the resolved config/service-catalog.yaml from -meta, matches PRD capabilities to service descriptions, generates a versioned impact-map artifact locally, and produces a PR-readiness handoff (handoff.forge for opendraftpr). Publish via…
Skill Claude Code
PM-lane purge: delete allowlisted meta working papers (Validation-Report, Resolution) for one initiative. Refuse KEEP paths (PRD, Impact-Map). Commit via Forge when pin requires it. No report file — success is handoff only. Independent of app/eng purge. No authorize-before-delete. Use Enter-at or…
Skill Claude CodeCodex
Interactively walks users through findings from any audit or validation report (validate-requirements, document-audit, or future skills). Reads the report file, detects its format, presents each finding as a decision brief (issue, example, recommendation+why, options with pros/cons) via AskQuestion, and produces a…
Skill Claude CodeCodex
Propagates approved corrections, decisions, terminology changes, and scope changes across related documents. In Resolution mode it consumes a review-findings Resolution file without re-deciding semantic choices; in Ad-hoc mode it first confirms the user-provided change set. Both modes perform impact analysis, present…
Skill Claude CodeCodex
Validates requirements documents using 15 checks across 2 dimensions: semantic accuracy (11 checks — source truth, inference detection, requirement purity, over-generalization, scope boundaries, testability, ambiguity, assumption dependencies, negative paths, actor capability, intra-document consistency) and…
Skill Claude Code
Score two or more PRD files independently against the spec-lane delivery bar, then compare. Use after /prd-think reruns, or whenever the user passes candidate paths (prd-think series or prd/{INIT}.md). Scientific: blind per-file PASS/FAIL with quoted evidence, then a comparison table. Optional companion /prd-critic is…
Skill Claude Code
Write a PRD by challenging the brief as a hypothesis, not by filling an outline. Grill job, actors, non-goals, and kill assumption; model the product; red-team; write a candidate as spec-draft input. Product ids from prayog-skills id-conventions. Writes reportsdir/{INIT}-prd-think.md (or -2, -3 on rerun). Use when…
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: