Plan & spec
10,724 rows, by stacks then stars
2,010 of these skill files have been read, by 1,360 distinct authors, and what they tell an agent counted. What Plan & spec authors agree on, and what they forbid
Finishing implementation elenchus
alexvtejeda/elenchus/skills/finishing-implementation-elenchus Skill
no license2★ repoUse when a frontend feature has been implemented and you want to verify it actually works in the running browser against its spec/plan — then fix what doesn't — before calling it done. Triggers: "verify my implementation works", "check the frontend against the spec", "did I actually build everything", "finish and verify this feature", "run the finishing pass". The post-execution stage of the Elenchus pipeline. NOT for stress-testing a build premise (elenchus-build), NOT for writing or verifying a plan (elenchus-plan), and NOT a code-style review.
shikanime-labs/skills/skills/workflow/to-spec Skill
2★ repoA curated catalog of self-improved agent skills for Hermes and compatible agents
Ken-Technology/cold-email-skills/search-strategy Skill
2★ repoTurn an ICP into portable prospect-search filters you can run in Apollo, Sales Navigator, Clay, ZoomInfo, or any list tool, plus the CSV shape for a bring-your-own list. Use when defining who to target for a cold-email campaign without a specific data provider. Triggers on "who should I target", "build my prospect filters", "define the ICP filters", or as the targeting step of the cold-email-campaign workflow.
carinyaparc/skills/skills/backlog-refine Skill
2★ repoUse to groom an existing backlog or judge whether a breakdown is ready to commit to — reprioritise, split oversized epics or stories, re-estimate, defer misaligned items, and check sprint readiness of docs/product/backlog.md or docs/work/{epic}/tasks.md. Triggers on "groom the backlog", "refine the backlog", "is this sprint-ready", "are these stories ready", "reprioritise", "this epic is too big", "clean up the backlog". Amends in place and reports a verdict. Do NOT use to create a backlog or write new stories and tasks (tasks), plan a sprint (sprint-planning), review a finished sprint (sprint-retro), or verify an epic against its acceptance criteria (validate).
carinyaparc/skills/skills/product Skill
2★ repoUse when the user wants a product strategy doc, PRD, pitch, vision, personas, or outcomes at docs/product/product.md. Drafts or re-authors the document. Triggers on "write the PRD", "draft a product pitch", "who are our personas". For reviewing or critiquing an existing product.md, use docs-review instead. Do NOT use for phased delivery plan (roadmap), epics or backlog (tasks), architecture (solution), tasks or Gherkin (tasks), or implementation (implement).
carinyaparc/skills/skills/roadmap Skill
2★ repoCarinya Parc Agent Skills
carinyaparc/skills/skills/solution Skill
2★ repoUse when the user wants to write system architecture at docs/architecture/solution.md (stub or full arc42-lite). Drafts or re-authors the document. Triggers on "write the architecture", "solution design", "arc42". For reviewing or critiquing an existing solution.md, use docs-review instead. Do NOT use for business strategy (product), delivery phases (roadmap), epic list (tasks), per-epic design.md (design), task Gherkin (tasks), or ADR files (adr write). Story AC belongs in docs/work/{epic}/tasks.md.
carinyaparc/skills/skills/sprint-planning Skill
2★ repoUse when the user wants to plan a sprint before it starts — set the sprint goal, pull committed scope from the backlog and epic tasks.md files, account for carry-over and capacity, and record dependencies, risks, and the sprint definition of done at docs/work/sprint-{id}/plan.md. Triggers on "plan sprint 3", "what should we commit to", "set up the next sprint", "sprint planning". Do NOT use to review a finished sprint (sprint-retro), write stories or task Gherkin (tasks), groom the backlog (backlog-refine), re-sequence delivery phases (roadmap), or sign off an epic (validate).
carinyaparc/skills/skills/sprint-retro Skill
2★ repoUse when the user wants to run a retrospective after a sprint ends — compare what was committed in plan.md against what actually shipped, surface themes with evidence, and record actions with owners routed to the skill that will action them, at docs/work/sprint-{id}/retrospective.md. Triggers on "run the retro", "sprint retrospective", "what went wrong last sprint", "how did sprint 3 go". Do NOT use to plan the next sprint (sprint-planning), sign off an epic against its acceptance criteria (validate), run a cross-document alignment pass (docs-review), or review a diff (code-review).
carinyaparc/skills/skills/tasks Skill
2★ repoUse to decompose anything into delivery work — a product strategy and roadmap into epics, an epic or its design into stories and tasks with Gherkin acceptance criteria, or an external spec, RFC, or PRD into both in one pass. Writes docs/product/backlog.md and docs/work/{epic}/tasks.md. Triggers on "break this spec into a backlog", "write the epics", "decompose checkout-foundation", "turn this RFC into tickets", "write tasks for CHK01", "what stories do we need". EARS with --ears. Do NOT use to groom an existing backlog or check sprint readiness (backlog-refine), write epic design (design), write architecture (solution), phase the delivery (roadmap), implement code (implement), or sign off an epic (validate).
bogdanbaciu21/skills/weekly-update Skill
2★ repoDraft a weekly stakeholder update for any software project. Use when the user asks for a weekly update, Friday email, status report, sprint summary, or stakeholder progress report. Pulls commits from git and issue counts from the project's tracker (GitHub Issues by default; Linear or Jira when an MCP server, API token, or CLI is available), asks a short set of clarifying questions, and produces a draft markdown file in docs/weekly-updates/. Optionally renders an HTML email using a brand template if one is configured.
jukrap/ai-agent-playbook/skills/database/schema-migration-plan Skill
2★ repoUse when planning or reviewing database schema migrations, DDL, indexes, constraints, defaults, nullability, seeds, views, triggers, or expand/contract rollout.
jukrap/ai-agent-playbook/skills/delivery/test-verification-strategy Skill
2★ repoUse when planning, reviewing, or repairing verification strategy, test scope, contract/manual checks, coverage gaps, risk-based selection, or release confidence.
jukrap/ai-agent-playbook/skills/design/design-brief-direction Skill
2★ repoUse when turning a vague product, page, brand, or UI request into a design direction, visual language, constraints, and decision-ready brief before implementation.
jukrap/ai-agent-playbook/skills/project/adr-spec-handoff Skill
2★ repoUse when turning decisions, architecture constraints, specs, milestone outcomes, worklogs, or implementation handoffs into durable ADR/spec/runbook/project-memory documentation.
jukrap/ai-agent-playbook/skills/project/issue-planning-triage Skill
2★ repoUse when converting specs, bugs, reviews, or worklogs into scoped issues and task batches.
jukrap/ai-agent-playbook/skills/project/requirements-prd-scope-review Skill
2★ repoUse when turning vague requests into PRDs, scope boundaries, acceptance criteria, or open questions.
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-approve Skill
2★ repoRecords the owner's approval of a reviewed spec so it enters the autonomous execution queue. Autonomous mode only - in supervised mode a plan with no open question is already approved, and this skill says so and stops.
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-audit-docs Skill
2★ repoAudit documentation claims against the code; report drift vs violation
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-cancel Skill
2★ repoCancel or supersede a spec, recording the reason so the decision is preserved
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-close Skill
2★ repoAfter merge, mark a spec completed and archive it per the project convention
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-continue Skill
2★ repoResume an in-progress spec: audit inherited work for drift, then continue execution
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-create Skill
2★ repoPlan a change as a reviewable spec: grill the owner, then write requirements, plan, tasks - the review gate before execution
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-decision Skill
2★ repoRecord a numbered ADR with context, decision, consequences, status
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-document Skill
2★ repoWrite or update one docs-substrate artifact - feature, rule, glossary, model, or architecture - from code, for owner review
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-execute-next Skill
2★ repoAutonomously pick the highest-value ready spec, drive it to an outcome-labeled PR, reset the workspace
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-execute Skill
2★ repoExecutes a planned spec via parallel subagents - one testable slice per subagent, gates re-run until dry. Supervised mode ends with unstaged changes for the developer's review; autonomous mode commits at milestones and ends at an outcome-labeled PR.
ainova-systems/intelligence-dev-packs/packs/spec/skills/spec-init Skill
2★ repoScaffold the in-repo docs substrate for spec-driven development and migrate existing docs into it, drafting core docs from code for owner review
lishix520/jtbd-skills/skills/jtbd-growth-strategist Skill
2★ repoMap quantitative Opportunity Scores and market evidence to candidate growth strategies (differentiated, dominant, disruptive, discrete, sustaining). Use when given opportunity calculation results, segment metadata, and structured price/cost/performance evidence, and asked to evaluate strategic positioning or disconfirming evidence. Do not use to invent market evidence or recommend product strategy without required prerequisites.
Truestack architecture planning
adtn0810/truestack/skills/truestack-architecture-planning Skill
2★ repoPlan the architecture and data flow for a feature, service, or system before any implementation code is written. Use this whenever the user is designing, scoping, or starting to build something new (backend or frontend) — even for a bare "build X" or "how should I structure this". This skill owns the design step wherever the chain starts — truestack-orchestrate enters first on requests that also need implementation or review and dispatches here, and the implementation itself belongs to truestack-backend-development once the plan is approved. Treats the request as intent to be clarified, picks the right architecture per project, sizes the planning ceremony to the work, and gates risky designs behind pre-work approval (orchestrate's gate is the post-work quality-control pass).
adtn0810/truestack/skills/truestack-backend-development Skill
2★ repoImplement backend code and recommend the best tech stack for the project at hand. Use whenever the user is writing server, API, or data-layer logic, choosing a language/framework/database, or asks to "build" or "code" a backend feature — even without an explicit stack question. Planning for a brand-new build starts in truestack-architecture-planning; this skill implements once a plan exists. Optimizes for data accuracy, performance, and not overloading a self-hosted single server.
sfrangulov/skills/consulting-problem-solving Skill
2★ repo**Consulting Problem Solving Framework**: An interactive, user-led approach to solving complex business and organizational problems using structured consulting methodology. You act as a consulting associate; the user acts as the consulting partner who drives decisions. Walks through problem definition, MECE structuring, prioritization, work planning, analysis, synthesis, recommendations, and communication — with the user providing input, making choices, and reviewing deliverables at every step before moving forward. Produces deliverables at each stage — markdown working docs, spreadsheets for data analysis, and final slide content (.md) or approved content for a vertical document. This skill owns content and structure only — visual rendering, styling, and deck/document generation are handled by downstream builder skills. All final prose is polished using an integrated Strunk & White writing style guide. Use this skill whenever the user mentions: strategy consulting, problem solving framework, issue tree, MECE, hypothesis-driven, pyramid principle, 80/20 analysis, root cause analysis, business case analysis, strategic recommendation, case interview prep, structured thinking, or any request to systematically break down and solve a complex problem. Also trigger when someone says things like 'help me think through this problem', 'I need a structured approach to X', 'how would a consultant approach this', or 'analyze this business situation'. Trigger when the request clearly calls for structured analytical problem solving with deliverables.
rumotion/ai-agent-project-template/.agents/skills/project-planner Skill
2★ repoCreates implementation plans from project requirements. Use when planning features, refactors, architecture changes, or multi-step development tasks.
rumotion/ai-agent-project-template/.cline/skills/project-planner Skill
2★ repoCreates implementation plans from project requirements. Use when planning features, refactors, architecture changes, or multi-step development tasks.
guofu-shiqu/ux-expert-skills/skills/exp-strategy-generation Skill
2★ repo体验策略生成。当已完成场景还原、旅程分析和洞察提炼,需要生成可执行的体验改善策略时调用。
b2bforce/b2bforce/.agents/skills/sales-bid-qualification Skill
2★ repoDecide bid, no-bid, or conditional on one opportunity by scoring the discovery brief against the service fit criteria and the ICP anti-fit criteria. Use before writing a proposal, when deciding whether to answer an RFP, or when the pipeline holds more requests than the firm can serve well.
b2bforce/b2bforce/.agents/skills/sales-discovery-brief Skill
2★ repoTurn call notes, an inbound email, or RFP text into a structured discovery brief for one opportunity, with a qualification verdict and the list of unanswered questions. Use when a prospect replies, a fit call happens, an RFP arrives, or before writing a proposal. Output to workspace/sales/opportunities/.
b2bforce/b2bforce/.agents/skills/sales-proposal Skill
2★ repoAssemble a B2B service proposal or SOW from the discovery brief, firm profile, service definition, ICP, and the verified proof library — with mandatory scope boundaries, assumptions, change control, and one pricing table. Use after a bid decision when the user needs a proposal, SOW, or RFP response.
r-irbe/proof-skills/skills/_overrides/lean-proof Skill
2★ repoUSE FOR: writing Lean 4 proofs one tactic at a time, fixing tactic errors by priority, planning sorry placeholders, cleaning a working proof, resolving dependent-type rewriting failures. DO NOT USE FOR: reviewing existing proofs (use @lean-proof-review), project-wide quality assessment (use @lean-quality-engine), minimising an error into a bug report (use @lean-mwe), discovering tactics or API (use @lean-research), authoring new theorem statements (use @lean-specification), repairing toolchains (use @lean-setup). TRIGGERS: prove, tactic, sorry, unsolved goals, motive is not type correct.
r-irbe/proof-skills/skills/applied-strategy-analysis Skill
2★ repoUSE FOR: Strategy creation, analysis, and evaluation — game-theoretic foundations, competitive analysis, decision frameworks, SWOT/PESTLE, wargaming, and their mathematical underpinnings. Use for strategic reasoning about complex multi-agent scenarios, organizational strategy, research strategy, and mathematical planning for governance and optimization layers. DO NOT USE FOR: formalising strategic models in Lean (use @lean-applied-reasoning); intelligence analysis (use @applied-intelligence-analysis); game-theoretic optimization (use @math-optimization-game). TRIGGERS: strategy, SWOT, PESTLE, wargaming, decision framework, competitive analysis, game-theoretic strategy.
r-irbe/proof-skills/skills/lean-applied-reasoning Skill
2★ repoUSE FOR: Applied reasoning for intelligence analysis, strategy creation and analysis, brainstorming methodologies, investigative reasoning, and domain-specific decision-making. Use when formalizing strategic frameworks, situational analysis, hypothesis generation workflows, decision-under-uncertainty models, or when connecting theoretical formalization to practical operational contexts. Bridges mathematical formalization to real-world application domains. DO NOT USE FOR: pure intelligence-analysis methodology (use @applied-intelligence-analysis); strategy analysis methodology (use @applied-strategy-analysis); legal reasoning methodology (use @applied-legal-reasoning). TRIGGERS: applied reasoning, intelligence formalisation, strategy formalisation, investigative reasoning, domain-specific reasoning.
r-irbe/proof-skills/skills/lean-doc-requirements Skill
2★ repoUSE FOR: Extract formal requirements from academic papers, technical reports, and design documents. Use when converting informal mathematical claims into Lean 4 theorem specifications. Covers claim extraction from LaTeX sources, equation identification, proposition mapping, hypothesis inference, and requirement traceability from document to formal specification. DO NOT USE FOR: paper update post-Lean (use @lean-doc-improvement); specification design (use @lean-specification); blueprint generation (use @lean-blueprint). TRIGGERS: doc requirements, requirement extraction, informal-to-Lean, claim extraction, paper-to-spec.
r-irbe/proof-skills/skills/lean-report Skill
2★ repoUSE FOR: converting a Lean 4 project blueprint into a publication-grade LaTeX report — blueprint artifact ingestion (extracted LaTeX nodes, dependency DAG, JSON metadata), per-chapter narrative generation with mathematical prose, dependency-driven cross-referencing, figure generation (dependency graphs, module maps, coverage tables), and LaTeX → PDF compilation via the 6-stage INGEST → PLAN → NARRATE → ILLUSTRATE → ASSEMBLE → COMPILE pipeline. DO NOT USE FOR: generating the blueprint itself (use @lean-blueprint); writing one chapter without the pipeline (use @lean-doc-improvement); reviewing a finished report (use @lean-review-council); spec lifecycle (use @lean-specification). TRIGGERS: blueprint to report, generate report, latex pdf, project-report.tex, narrate chapter, dependency figure, blueprint compile.
r-irbe/proof-skills/skills/lean-review-council Skill
2★ repoUSE FOR: orchestrating a 5-member Lean 4 proof review council (Σ Kernel Guardian, Φ Statement Oracle, Ν Novelty Scout, Λ Quality Architect, Ω Integration Sentinel); running RALPH (Review-Analyze-Learn-Plan-Handle) loops at member / council / project / meta scales; structured voting with structured-disagreement-resolution (SDR); council topology selection (Star / Pipeline / Mesh / Hierarchical / Swarm / Ring / Hub-Spoke); maximum-parallel agent dispatch with cascading completion handlers; specification lifecycle (requirements → design → docs); inter-council collaboration; Zettelkasten knowledge synthesis; calibration scoring; enforcement tactics. DO NOT USE FOR: reviewing one Lean proof in isolation (use @lean-proof-review); writing a proof (use @lean-proof); running CI scripts (use @lean-enforcement); single-skill council convocation when no multi-layer review is needed (use the relevant skill directly). TRIGGERS: review council, RALPH loop, council vote, SDR, council topology, kernel guardian, statement oracle, novelty scout, quality architect, integration sentinel, meta-council, council session.
r-irbe/proof-skills/skills/lean-specification Skill
2★ repoUSE FOR: Design theorem specifications for Lean 4 proofs. Use when planning new theorems, lemmas, definitions, or tactics. Covers the three-part specification (requirements, design, documentation), lifecycle management, dependency analysis, and integration with the review council. DO NOT USE FOR: actual proof writing (use @lean-proof); requirement extraction (use @lean-doc-requirements); review (use @lean-proof-review). TRIGGERS: specification, theorem spec, three-part spec, lemma plan, tactic plan.
r-irbe/proof-skills/skills/math-product-management Skill
2★ repoUSE FOR: Product management for mathematical formalization projects — roadmap creation, stakeholder management, feature prioritization for formal verification artifacts, theorem portfolio management, release planning, and the business/academic value analysis of formal proofs. Complements math-project-management (scheduling/execution) with strategic product thinking. DO NOT USE FOR: project-level scheduling (use @math-project-management); strategy methodology (use @applied-strategy-analysis); engineering discipline view (use @applied-engineering-disciplines). TRIGGERS: product management, roadmap, stakeholder management, feature prioritization, formal verification PM.
r-irbe/proof-skills/skills/math-strategy-studio Skill
2★ repoUSE FOR: Strategic mathematical thinking — brainstorming, problem decomposition, proof strategy design, creative hypothesis generation, and mathematical intuition development. Use when facing novel formalization challenges, when standard approaches fail, when exploring connections between domains, or when the theorem specification needs creative mathematical insight. The creative counterpart to the systematic research-council and review-council skills. DO NOT USE FOR: strategy analysis methodology generally (use @applied-strategy-analysis); research synthesis (use @research-synthesis-engine); Lean specification (use @lean-specification). TRIGGERS: strategy studio, brainstorming, problem decomposition, proof strategy, creative hypothesis, mathematical intuition.
JeanIsahakyan/skills/plugin/skills/simulate Skill
no license2★ repoStress-test a spec or design doc BEFORE writing code by mentally executing it end-to-end — acting simultaneously as every component (data stores, caches, services, clients, external systems, transports), tracking explicit state diffs after every step, and running golden, edge, and adversarial scenarios until findings settle to LOW severity. Use this skill whenever the user has a spec / design doc / RFC / PRD and wants to validate it before building: "simulate this spec", "stress-test this design", "act as every component", "walk through every flow", "pretend you are the whole system", "find the holes / races / edge cases in this design", "is this spec internally consistent", "check for ambiguities / contradictions / missing rules before we implement". It runs a spec-analyzer → parallel scenario-simulators → findings-aggregator loop autonomously (no questions mid-run), one file per scenario, and produces a deduped, severity-ranked FINDINGS.md. Best for any non-trivial design with state, concurrency, auth, money, or external systems — exactly where spec bugs hide.
JeanIsahakyan/skills/plugin/skills/spec Skill
no license2★ repoTurn a fuzzy product idea into a precise, written feature spec / PRD BEFORE any code — by interviewing the user with plain-language PRODUCT questions only and deriving every technical decision automatically from the existing codebase (never asking the user a tech question). The output is a single SPEC.md with a hard wall: narrative product behaviour on top (reads like a PM wrote it), a derived technical appendix sealed at the bottom (reads like an engineering handoff). Use this whenever the user wants to spec a feature, write a PRD, formalize requirements, design a flow, document how a behaviour should work, or turn a vague ask into a contract before implementation: "spec this", "write a spec for X", "design the X flow", "PRD for X", "how should this feature work", "let's spec out X", "formalize requirements for Y". Runs a codebase-context agent (reads the repo) + a product-interviewer loop (open-ended questions until coverage converges) + a spec-writer agent. Best for any non-trivial feature where the product intent is fuzzy but the stack is already established.
john-data-chen/hermes-agent-backup/skills/software-development/plan Skill
2★ repoPlan mode: write an actionable markdown plan to .hermes/plans/, no execution. Bite-sized tasks, exact paths, complete code.
The same file is in 1 other repository
xAmirHamza77/PenKit51/skills/engagement-planning Skill
no license2★ repoRules of engagement, scope definition, and authorized penetration test planning
TeamDzX/myllm-skills/skills/research-brief Skill
2★ repoAnswer a question with a short, sourced research brief. Use for "research X", "what's the latest on Y", or fact-finding that needs citations.
kimgoetzke/coding-agent-configs/skills/fetch-plan Skill
2★ repoRetrieve saved plan folders from `.ai/planning`, let the user choose one, then load its planning documents and summarise implementation status. Use when user asks to fetch, reopen, resume, continue, or inspect an existing plan.
kimgoetzke/coding-agent-configs/skills/improve-a-plan Skill
2★ repoReview, criticise and/or test an existing plan with the goal of improving is. Use when user asks you to review or improve a plan.
kimgoetzke/coding-agent-configs/skills/planning-mode Skill
2★ repoToggle persistent planning mode on/off. When on, hook support can remind the agent to keep planning documents updated throughout the conversation, with manual fallback if unavailable. Combines the full planning workflow with persistent mode for long-running planning and implementation sessions. Use with a topic to start, with "continue" to resume an existing plan, or with "off" to stop.
kimgoetzke/coding-agent-configs/skills/planning Skill
2★ repoPlanning a change to any codebase. Use when user asks you to plan something instead of taking immediate action.
kimgoetzke/coding-agent-configs/skills/update-plan Skill
2★ repoUpdates planning documents created using the planning-mode or planning skill after questions.md has been updated by the user. Supports an interactive `ask` mode that prompts the user for any still-unanswered questions in real-time. Use when user asks to update the plan after answering your questions, or when they want to walk through unanswered questions interactively.
maurigre/mgr-method/skills/spec-create Skill
no license2★ repoImplements the full SDD flow to EVOLVE a project already initialized by spec-init - receives a feature, bugfix or refactor brief, generates the PRD, technical spec and task plan with blocking human checkpoints, and after approval delegates the implementation to the spec-execute skill and, on closing, records the AI-First evidence via evidence-capture when the project policy enables it (no automatic commit). Use whenever the user asks to add or implement a feature, fix a bug with SDD, refactor preserving behavior, create a spec and implement it, or resume a feature in progress. Requires /docs/sdd/ and CONSTITUTION.md to exist.
maurigre/mgr-method/skills/spec-execute Skill
no license2★ repoExecutes the approved plan of an SDD feature (specs/<feature>/04-plan.md) task by task, respecting the dependency DAG and the P0/P1/P2 priorities, applying the development premises (security, performance, resource usage, clarity) and active context control (tiers, hand-off). Invoked by spec-create after plan approval, or directly to resume an interrupted execution. Use when the user asks to execute the plan, implement the approved tasks, continue or resume a feature's implementation. Requires an approved plan; no automatic git action.
maurigre/mgr-method/skills/spec-init Skill
no license2★ repoInitializes a project's SDD (Specification-Driven Development) structure. On an EXISTING project, runs a phased deep analysis with chunking and generates /docs/sdd/ (00-overview to 08-glossary), CONSTITUTION.md and the review rules guide. On an EMPTY project (greenfield), conducts a guided interview about stack/architecture/domain and generates the same artifacts from the choices. Use whenever the user asks to analyze, document or map a project, generate SDD, extract contracts, onboard a repository, start a project from scratch with SDD, or generate instructions for Copilot/Cursor. Prerequisite of the spec-create skill.