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
MadewellRD/skills-lab/dist/vendor/openai/product-command-desk/gtm-brief-desk Skill
2★ repocreate go-to-market briefs with audience, positioning, messaging, channels, sales and support enablement, launch risks, success metrics, and product handoffs.
MadewellRD/skills-lab/dist/vendor/openai/product-command-desk/prd-desk Skill
2★ repocreate product requirements documents with problem statement, goals, non-goals, users, requirements, acceptance criteria, risks, open questions, metrics, and downstream handoffs.
MadewellRD/skills-lab/dist/vendor/openai/product-command-desk/product-command-desk Skill
2★ repoorchestrate product workflows from idea, market or customer signal, and business objective through discovery, requirements, prioritization, roadmap, launch, experimentation, feedback, retention, and retrospective stages.
MadewellRD/skills-lab/dist/vendor/openai/product-command-desk/roadmap-planning-desk Skill
2★ repocreate roadmap plans with themes, sequencing, milestones, dependencies, capacity constraints, confidence, risks, decision records, and delivery handoffs.
MadewellRD/skills-lab/dist/vendor/openai/sales-command-desk/proposal-desk Skill
2★ repocreate customer-facing proposal, scope, deck, docx, and pdf drafts with brand, pricing, and approval controls. use when ChatGPT needs to perform or continue sales revenue command desk work involving accounts, leads, opportunities, crm, calendar, email, files, prospecting, proposals, forecasts, renewals, or customer handoffs.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/goliveprompt Skill
2★ repogenerate and run the go-live protocol for a software project, covering total repo reconnaissance, status assessment, engineering spec, a full sdlc-command-desk audit hard gate, a sprint-split roadmap with GL ids and acceptance gates, a pinned live tracker artifact, and by-the-book github execution. use whenever the user types /goliveprompt, asks for a go-live prompt, plan, roadmap, or tracker, wants a repo taken to production, wants a project scanned end to end before implementation begins, wants work split into sprints, or wants lifecycle discipline retrofitted onto a project already in flight.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/issue-planning-desk Skill
2★ repocreate connector-grounded issue plans, github issue drafts, dependency graphs, milestone breakdowns, labels, sequencing, acceptance gates, and downstream handoff notes from prds, discovery memos, architecture specs, design docs, repo state, and stakeholder decisions. use when ChatGPT needs to turn requirements or design intent into actionable implementation work, sprint scope, issue decomposition, issue bodies, dependency ordering, or implementation-handoff-desk handoff material.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/product-requirements-desk Skill
2★ repocreate connector-grounded product requirements documents for software work. use when the user needs a prd, requirement ids, acceptance criteria, non-goals, risks, open questions, source facts, stakeholder decision synthesis, or downstream handoff notes before technical discovery, architecture, issue planning, implementation, testing, verification, or release work.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/retrospective-desk Skill
2★ repocreate connector-grounded retrospectives and continuous-improvement artifacts for software delivery. use when ChatGPT needs to synthesize sprint, release, incident, pull request, ci, deployment, product, or team evidence into a retrospective report, lessons-learned memo, process-improvement plan, cycle-metrics summary, action-item tracker, or downstream handoff notes for product, architecture, issue planning, implementation-handoff-desk, release, ci, incident, or documentation workflows.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/technical-discovery-desk Skill
2★ repocreate connector-grounded technical discovery memos, repo reconnaissance reports, feasibility assessments, spike plans, risk registers, unknowns lists, and downstream handoff notes before architecture or implementation work. use when the user asks to investigate technical feasibility, inspect a repo before planning, research dependencies or integrations, compare implementation options, identify unknowns, map risks, plan a spike, or prepare technical input for architecture-design-desk, issue-planning-desk, or implementation-handoff-desk.
MadewellRD/skills-lab/dist/vendor/openai/sdlc-command-desk/test-strategy-desk Skill
2★ repocreate connector-grounded test strategies, qa scenario matrices, regression plans, fixture plans, coverage-gap reports, and verification handoff notes from product requirements, architecture specs, issue plans, pull requests, repository tests, ci results, bug reports, and known regressions. use when ChatGPT needs to define what should be tested, map requirements to test coverage, identify missing tests, plan regression scope, design fixtures, classify test risk, or prepare downstream handoff notes for verification-desk, review-quality-desk, ci-failure-desk, or implementation-handoff-desk workflows.
Cryptography key management desk
MadewellRD/skills-lab/dist/vendor/openai/security-command-desk/cryptography-key-management-desk Skill
2★ repodefine and review cryptographic posture, covering the approved algorithm protocol and cipher suite set with dated deprecations, tls and transport configuration, encryption at rest and envelope key hierarchies, password hashing and key derivation, key custody in hardware modules with dual control, cryptoperiods and rotation, certificate lifecycle issuance renewal and revocation, signing and jwt key rollover, and the cryptographic agility and post-quantum migration plan. use for crypto standard definition, tls posture review, key management design, certificate expiry and ownership gaps, and algorithm deprecation planning.
MadewellRD/skills-lab/dist/vendor/openai/sre-reliability-command-desk/capacity-planning-desk Skill
2★ repobuild the demand model and its drivers, measure headroom against the binding saturation signal rather than average cpu, find quota connection partition thread and licence ceilings, state provisioning lead time, compute failover headroom at real peak, and separate every measured number from every assumed one. use for capacity planning, headroom analysis, saturation signals, scaling limits, quota exhaustion, and peak readiness.
MadewellRD/skills-lab/dist/vendor/openai/sre-reliability-command-desk/sli-specification-desk Skill
2★ repospecify service level indicators per critical user journey including the good-event and valid-event definitions, the measurement point and its bias, the implementation query or export behind each indicator, and the split between measured, partially measured, and unmeasured. use for sli definition, event counting, availability latency freshness correctness indicators, measurement point selection, and instrumentation gap analysis.
MadewellRD/skills-lab/dist/vendor/openai/sre-reliability-command-desk/sre-reliability-command-desk Skill
2★ repoorchestrate site reliability engineering work across slis, slos, error budgets, capacity planning, load and performance testing, chaos and resilience testing, dependency and failure-mode analysis, disaster recovery, backup and restore, alerting quality, runbooks, on-call and escalation, production readiness review, change safety, incident command, postmortems, and toil reduction. use when the user wants to set reliability targets, run or review a production incident, plan capacity, harden a service against failure, prove recovery, tune paging and reduce alert noise, cut operational load, or gate a launch on readiness.
Site product requirements desk
MadewellRD/skills-lab/dist/vendor/openai/web-development-command-desk/site-product-requirements-desk Skill
2★ repocreate web-specific product requirements, page and route scope, user journeys, acceptance criteria, success metrics, analytics intent, source facts, risks, open questions, and downstream handoff notes for websites, web apps, landing pages, portals, dashboards, docs sites, ecommerce surfaces, and admin ui work. use before information architecture, design, engineering, testing, release, or growth work when scope is not already accepted.
jonisavo/supersigil/.agents/skills/ss-feature-specification Skill
2★ repoDefault skill for authoring or repairing Supersigil specification documents: requirements, design docs, tasks, and ADRs. Use when turning an agreed feature idea or imported material into verifiable docs, refining acceptance criteria, or bringing specs to an implementation-ready state. Works alongside brainstorming and planning skills.
jonisavo/supersigil/.agents/skills/ss-retroactive-specification Skill
2★ repoUse when code exists but Supersigil specs do not, or when existing specs have gone stale. Activates when the user wants to document current behavior, baseline before a refactor, add spec coverage to a brownfield module, or reconcile drifted specs with the codebase.
jonisavo/supersigil/.agents/skills/ss-spec-driven-development Skill
2★ repoUse ONLY when the user explicitly requests the full end-to-end Supersigil workflow — from feature idea through verified specs to implementation. This is the guided "omakase" flow. For just writing specs, use ss-feature-specification. For just implementing, use ss-feature-development.
Fodhol/skills/plugins/spec-to-code-compliance/skills/spec-to-code-compliance Skill
2★ repoVerifies code implements exactly what documentation specifies for blockchain audits. Use when comparing code against whitepapers, finding gaps between specs and implementation, or performing compliance checks for protocol implementations.
Cinderfi — Retirement Planning
cinderfi/cinderfi-mcp/com.cinderfi/retirement-planning MCP server
no license2★ repoRetirement planning for Canada & US. CPP/OAS, Social Security, RRSP/TFSA, 401k/IRA, Monte Carlo.
toRolex/rolex-skills/skills/engineering/qa-plan Skill
1★ repo根据最近一批 commit 生成 step-by-step QA 测试计划,并保存为 GitHub issue。用户通过 /qa-plan 调用。
toRolex/rolex-skills/skills/engineering/to-spec Skill
1★ repo将当前对话转化为 spec 并发布到项目 issue tracker——无需访谈,只需综合你已经讨论过的内容。
grandheman/claude-sdlc/skills/product-manager Skill
1★ repoUse this skill whenever the task involves product management activities: writing or refining a PRD, authoring user stories, defining acceptance criteria, prioritizing a backlog, creating a product roadmap, writing stakeholder updates, or analyzing feature requests. Triggers on: "write a PRD", "define requirements", "user stories", "acceptance criteria", "backlog", "roadmap", "feature request", "prioritize", "stakeholder update", "product spec". Also use when a developer or engineer asks "what exactly should this feature do?"
grandheman/claude-sdlc/skills/project-manager Skill
1★ repoUse this skill for project management activities: sprint planning, status reporting, risk management, milestone tracking, retrospectives, standups, dependency management, and team coordination. Triggers on: "sprint planning", "status report", "project status", "track progress", "risk register", "retro", "retrospective", "standup", "milestone", "dependencies", "blocked", "escalate", "project plan", "velocity", "capacity planning", "action items", "meeting notes". Also triggers when the user needs to organize, coordinate, or report on work in progress.
grandheman/claude-sdlc/skills/qa-engineer Skill
1★ repoUse this skill for any quality assurance task: writing test plans, creating test cases, filing bug reports, performing test execution, defining quality gates, or planning regression testing. Triggers on: "write test cases", "test plan", "QA", "file a bug", "bug report", "how do I test this", "regression testing", "acceptance testing", "test coverage", "quality gate", "sign off on this", "validate this feature". Also use when reviewing PRD acceptance criteria to ensure they are testable.
grandheman/claude-sdlc/skills/release-manager Skill
1★ repoUse this skill for anything related to managing or preparing a software release: release checklists, release notes, version bumping, release planning, go/no-go decisions, changelog maintenance, deployment coordination, or rollback planning. Triggers on: "prepare a release", "release notes", "write the changelog", "version bump", "deploy to production", "release checklist", "go/no-go", "rollback plan", "release planning", "ship this", "release process", "cut a release". Use for both major releases and patch/hotfix releases.
grandheman/claude-sdlc/skills/tech-lead Skill
1★ repoUse this skill for tech lead responsibilities: breaking down epics into tasks, creating technical design documents, setting code standards, making day-to-day technical decisions, maintaining the tech debt register, and mentoring developers. Triggers on: "break this down into tasks", "technical design", "TDD", "how should we implement", "sprint breakdown", "task estimation", "code standards", "tech debt", "sprint planning", "implementation plan", "developer handoff". Use after architecture is defined and before development begins.
dss-time/repo-doctor-skills/plugins/productivity-toolkit/skills/research-brief Skill
1★ repoDefine and answer a bounded research question with a source plan, evidence ledger, cross-checking, conclusions, unknowns, and next steps. Use when gathering or synthesizing evidence is the primary task; use report-writer when supplied material only needs a polished report, and never claim current research without accessible sources or network capability. 围绕有边界的研究问题制定来源计划、建立证据台账、交叉验证并输出结论、未知项和下一步。主要任务是搜集或综合证据时使用;已有材料只需形成正式报告时使用 report-writer;无法访问资料或网络时不得声称完成实时研究。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/repo-doctor-router Skill
1★ repoClassify the current repository task and recommend one existing Repo Doctor Skill or an ordered workflow without executing it. Use when the user is entering an unfamiliar repository, is unsure which Skill to choose, or needs the next safe step across clarification, specification, planning, implementation, testing, review, diagnosis, release readiness, or session transfer; do not use for ordinary questions with no repository workflow decision. 对当前仓库任务分类,并推荐一个现有 Repo Doctor Skill 或有序工作流,但不执行被推荐能力。用于初次进入陌生仓库、不知道选择哪个 Skill,或需要在澄清、规格、计划、实施、测试、审查、诊断、发布检查与会话交接之间选择安全下一步;普通问答不涉及仓库工作流决策时不要触发。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/requirements-clarification Skill
1★ repoResolve the material product, behavior, compatibility, data, permission, security, migration, and acceptance decisions that remain open before specification or implementation. Use when a request contains consequential ambiguity; inspect repository evidence before asking one focused question at a time, then produce a clarification summary for requirements-to-spec. Do not use for an already clear small change, write the final specification, edit long-term documentation, or implement code. 在规格化或实施前,关闭仍未确定且会实质影响产品、行为、兼容性、数据、权限、安全、迁移和验收的决策。用于存在关键歧义的需求;先检查仓库证据,再一次聚焦一个问题,最终生成交给 requirements-to-spec 的澄清摘要。已清楚的小改动不使用,也不生成最终规格、不修改长期文档或实施代码。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/requirements-to-spec Skill
1★ repoConvert requirements whose material product, data, security, permission, compatibility, and acceptance decisions are already closed into a structured, implementable, testable specification. Use when a clarification summary or settled discussion is ready for specification and only non-blocking assumptions remain; stop and route material open decisions to requirements-clarification. Do not use for task decomposition, implementation planning, code explanation, bug fixing, or direct edits. 将产品、数据、安全、权限、兼容性和验收等重大决策已经闭合的需求整理为结构化、可实施、可验证的规格。用于已有澄清摘要或讨论已定稿、只剩非阻塞假设时;发现重大未决决策必须停止并转交 requirements-clarification。不用于拆工作项、制定实施计划、解释代码、修 Bug 或直接修改。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/safe-change-plan Skill
1★ repoTurn a confirmed specification, root-cause finding, or impact analysis into an atomic, verifiable, reversible implementation plan with explicit scope and risk controls. Use only when material decisions are closed and blast radius is sufficiently known; route open decisions to requirements-clarification, settled requirements needing a specification to requirements-to-spec, unknown impact to change-impact-analysis, architecture rationale or decision documentation to architecture-decision-record, and execution to safe-fix-implementation. 将已确认规格、根因结论或影响分析转为原子化、可验证、可回滚且范围明确的实施计划。仅在重大决策已闭合且影响范围足够明确时使用;未决需求交给 requirements-clarification,已闭合但尚需规格化的需求交给 requirements-to-spec,影响未知交给 change-impact-analysis,架构理由或决策文档交给 architecture-decision-record,执行交给 safe-fix-implementation。
dss-time/repo-doctor-skills/plugins/repo-doctor/skills/spec-to-work-items Skill
1★ repoDecompose a confirmed specification, implementation plan, or settled conversation into independently executable and verifiable vertical work items with dependencies, safe parallelism, conflict areas, tests, risks, and rollback notes. Use for delivery planning of a multi-behavior scope; return copyable Markdown in the current response only and never write files, invoke Shell, or create external tasks even with user authorization. Do not use for unresolved requirements, a single small fix, or a file-by-file technical-layer checklist. 将已确认规格、实施计划或已闭合对话拆成可独立执行和验证的垂直工作项,明确依赖、安全并行、冲突区域、测试、风险和回滚。用于包含多个可交付行为的交付规划;只在当前响应返回可复制 Markdown;即使用户授权也不写文件、不调用 Shell、不创建外部任务。需求未闭合、单个小修复或按文件与技术层罗列清单时不使用。
AnotherSava/claude-code-common/claude/skills/plan-ralphex Skill
1★ repoCreate an implementation plan for a new feature, refactor, or fix. Guides an interactive design discussion and produces a structured plan document.
prvthmpcypher/skills-personal/skills/travel-planner Skill
1★ repoYou are an expert travel planner. When given destination, dates, and budget, create a comprehensive travel itinerary with day-by-day activities, logistics, accommodation recommendations, and budget breakdown. ## Process 1. Understand the destination, dates, budget, and travel style 2. Research and plan day-by-day activities 3. Calculate transportation and logistics 4. Recommend accommodation options 5. Create a detailed budget breakdown ## Output Format ## Travel Itinerary: \[Destination\] ### Trip Overview - Destination: \[City, Country\] - Dates: \[Start\] to \[End\] - Duration: \[X days\] - Budget: \$\[Total\] - Travelers: \[Solo/Couple/Family/Group\] ### Day-by-Day Itinerary Day 1: Arrival & \[Area\] - Morning: Arrive, check in, get oriented - Afternoon: \[Activity\] - Evening: \[Restaurant/Area to explore\] - Transport: \[Airport to accommodation\] Day 2: \[Theme\] - Morning:...
ronniepinnell/casper/collection/planning-and-lifecycle/ccb Skill
1★ repoChange Control Board — executive review that audits project state, prioritizes work, and plans the next milestone. Spawns adversarial agents (completion-audit, spec-audit, PM, architect) for scrutiny. Use when starting a new milestone or major planning cycle.
ronniepinnell/casper/collection/planning-and-lifecycle/milestone Skill
1★ repoMilestone lifecycle — start, status, close. Wires the shared lifecycle narrative blocks. A milestone is a coherent slice of work with multiple epics + a CLEANUP epic at the end.
ronniepinnell/casper/collection/planning-and-lifecycle/plan-milestone Skill
1★ repoBreak a milestone goal into epics and tasks with dependency ordering, acceptance tests, and task manager ticket creation. Works with any task manager via the adapter layer.
ronniepinnell/casper/collection/verification-and-audit/completion-audit Skill
1★ repoSession/project-scope reality audit. Independently establishes how much of the claimed-done work is genuinely functional, cross-checked against every planning source, and produces a prioritized remediation plan. Use before committing or closing issues, when statuses say done but the system misbehaves, or whenever an honest project snapshot is needed. Supports --task <id> for single-task scope.
ronniepinnell/casper/collection/verification-and-audit/dossier Skill
1★ repoFrontier dossier session — run a repo's deepest available review with the strongest available model and bank ALL of it in one committed, append-only file. Spec-truth pass, graded deep review, executable fix rulings, a FULL build-to-spec plan, product/feature/tech ideation with gap analysis, and a premortem. Use when frontier-model time is scarce and its judgment must survive as a permanent artifact; rerun periodically and diff against the last section.
ronniepinnell/casper/collection/verification-and-audit/spec-audit Skill
1★ repoCode-vs-spec comparator. Reads the source first-hand and compares it against written specification documents, classifying every divergence as absent, partial, wrong, or extra — with file:line on both sides and an explicit call on which artifact should change. Project rules (CLAUDE.md) outrank specs. Use before PRs, after spec'd feature work, or when spec drift is suspected.
foxgeeek/adskills/.claude/skills/meta-ads/creative-strategy Skill
1★ repoBulk upload Meta Ads creatives from local folder or Google Drive, generate copy variations (headlines, primary text, descriptions), and structure ad sets by creative angle. Use when user asks to upload creatives, create ads in bulk, or launch campaigns from a batch of assets.
OthmanAdi/gmira/skills/gmira-brief Skill
1★ repoUse when starting any web surface and no written brief exists yet: a new landing page, a vehicle inventory site, a product detail page, a course or cohort page, a dashboard, a portfolio, a checkout. Also use when a build is about to invent content it has no right to invent (prices, customer names, logos, benchmarks, seat counts, review scores), when the requested page turns out to be several surfaces with different jobs, or when a first draft came back generic because nobody wrote down what is actually true. Extracts product truth against aspiration, the visitor scene, the real content model field by field, the surface mode, and the uninventable list, then commits all of it to `.gmira/surfaces/<slug>.md`. Run it before `gmira-direction`, every time, including on "just fix the hero".
aimasteracc/harness-kit/skills/subagent-brief Skill
no license1★ repoWrite a sub-agent brief that survives the messaging asymmetry — explicit inputs, explicit outputs, and a degraded-mode paragraph so the sub-agent completes instead of silently stalling. Use when the user says "brief a sub-agent", "spawn an agent to…", "subagent brief", or is designing a multi-agent / swarm step.
Speckledrattlesnakeinoculant470/claude-for-researchers/starter/.claude/skills/sync-brief Skill
no license1★ repoOptimize Claude Code workflows for long-term physics and mathematics research projects with structured toolkits and practical guidance.
broneq/bdk/skills/create-plan Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
broneq/bdk/skills/execute-plan Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
broneq/bdk/skills/subagent-execute-plan Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
broneq/bdk/skills/verify-plan Skill
1★ repoBDK — Broneq Dev Kit. Reusable Claude Code workflows: skills, agents, and hooks for TDD, planning, code review, and architecture documentation.
fagemx/prismstack/skills/domain-plan Skill
1★ repo為目標領域推導完整的 gstack skill map + workflow + artifact flow。 Trigger: 用戶說「我做 X 領域」、「幫我規劃 skill」、「我想建一套 domain stack」。 Do NOT use when: 已經有 skill map,要搭建(用 /domain-build)。 Do NOT use when: 要加單一 skill(用 /skill-gen)。 上游:無(入口 skill)。 下游:/domain-build。 產出:skill-map-{datetime}.md + workflow-graph-{datetime}.md
bitcoin21ideas/skills/skills/plan-clash Skill
1★ repoHarden an existing implementation plan via a fixed N-round cross-model critique→fold loop. A codex (GPT) subprocess critiques the plan against the real code; a claude (opus) subprocess rules on each finding and folds accepted fixes into a copy. Use when the user explicitly asks to harden, stress-test, clash, or improve a written plan before building — e.g. "plan-clash this", "harden this plan". It improves a plan; it never certifies one — the human judges "good enough".
bitcoin21ideas/skills/skills/pressure-test Skill
1★ repoInterviews the user relentlessly about a plan, design, or proposal until shared understanding is reached, walking the decision tree branch by branch and resolving dependencies one at a time. Use when the user asks to stress-test, pressure-test, grill, interrogate, or challenge a plan, design, or proposal; or when the user says "pressure-test this", "grill me", or "interview me on this plan". Works for code, infrastructure, product, content, research, or any plan with branching decisions.
bitcoin21ideas/skills/skills/to-plan Skill
1★ repoSynthesize a decisions record and the current codebase into a pure implementation plan written to disk. Use when the user asks to turn a plan, spec, or set of decisions into an implementation plan, or says "to-plan this", "write a plan", "make a plan from this".
scoobydont-666/shared-claude-skills/skills/prd-to-plan Skill
1★ repoTurn a PRD into a multi-phase implementation plan using tracer-bullet vertical slices, saved as a local Markdown file in ./plans/. Use when user wants to break down a PRD, create an implementation plan, plan phases from a PRD, or mentions "tracer bullets".
The same file is in 4 other repositories
scoobydont-666/shared-claude-skills/skills/write-a-prd Skill
1★ repoCreate a PRD through user interview, codebase exploration, and module design, then submit as a GitHub issue. Use when user wants to write a PRD, create a product requirements document, or plan a new feature.
The same file is in 3 other repositories
vstakhovsky/shokunin-review/.claude/skills/shokunin-strategy Skill
no license1★ repoTerminal-first validation harness for reviewing PRDs, RFCs, strategy docs, and experiment plans.
vstakhovsky/shokunin-review/skills/shokunin-review-prd Skill
no license1★ repoReview PRDs for problem clarity, evidence, MVP scope, metrics, requirements, risks, and decision-readiness.
RealDougEubanks/ClaudeMarketplace/skills/agent-based-development/skills/abd-plan Skill
1★ repoABD Planning agent: bootstraps projects, assigns tasks to agents, and updates plan artifacts. Run /abd-triage to triage review findings.
darbin/claudecraft/plugins/rem-dev-core/skills/rem-plan Skill
1★ repoWrite a verification-first implementation plan that a fresh subagent could execute without session context. Audits existing capabilities before proposing new code, validates the riskiest assumption first, and gives every task a verification primitive matching its kind. Distinct from rem-review-plan (validates an existing plan) and rem-execute (runs an approved plan). Use for "plan", "implementation plan", "write a plan", "how should we build X", "break this down", "plan this feature", "plan the refactor", or any non-trivial feature, bug fix, or refactor.