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
gmmh1/claude-paid-media-skills/skills/google-ads-strategy Skill
0★ repoDecide whether and how to use Google Ads before anything gets built. Triggers on 'should I use Google Ads', 'what Google Ads campaign type should I run', 'plan my Google Ads funnel', 'how much budget for Google Ads', or 'Google Ads strategy for [business]'. Answers channel/objective/budget questions at the planning layer — hands off to google-ads-campaign-builder for execution.
gmmh1/claude-paid-media-skills/skills/linkedin-ads-strategy Skill
0★ repoDecide whether and how to use LinkedIn Ads before anything gets built. Triggers on 'should I use LinkedIn Ads', 'what LinkedIn objective should I run', 'plan my LinkedIn B2B funnel', or 'LinkedIn Ads strategy for [business]'. Planning layer — hands off to linkedin-ads-campaign-builder for execution.
gmmh1/claude-paid-media-skills/skills/meta-ads-creative-strategy Skill
0★ repoDevelop Meta ad creative concepts and formats — feed, Stories, Reels, carousel, collection — and creative angles/hooks. Triggers on 'Meta creative strategy', 'what creative angles should I test', 'carousel ad concept', or 'creative brief for Facebook/Instagram'. Strategic/format layer — for video-specific hook mechanics see meta-ads-video-reels, for copy see meta-ads-copywriting.
gmmh1/claude-paid-media-skills/skills/meta-ads-strategy Skill
0★ repoDecide whether and how to use Meta Ads before anything gets built. Triggers on 'should I use Facebook/Instagram Ads', 'what Meta campaign objective should I run', 'plan my Meta Ads funnel', or 'Meta Ads strategy for [business]'. Planning layer — hands off to meta-ads-campaign-builder for execution.
gmmh1/claude-paid-media-skills/skills/paid-media-strategy Skill
0★ repoMaster router for cross-platform paid media strategy — deciding across Google, Meta, LinkedIn, TikTok, Amazon and other channels, budget allocation, and cross-channel audits. Triggers on 'which platform should I advertise on', 'allocate my paid media budget', 'cross-channel advertising strategy', or any paid-media question spanning more than one platform. Sits above google-ads, meta-ads, linkedin-ads, and tiktok-ads — routes into those for platform-specific execution.
gmmh1/claude-paid-media-skills/skills/tiktok-ads-creative-strategy Skill
0★ repoDevelop TikTok ad creative concepts — native video hooks, UGC angles, and trend-aware formats. Triggers on 'TikTok creative strategy', 'what hooks should I test on TikTok', 'creative brief for TikTok Ads', or 'why isn't my TikTok ad performing'. Strategic/format layer — for scripting specific videos see tiktok-ads-copywriting-scripts.
gmmh1/claude-paid-media-skills/skills/tiktok-ads-strategy Skill
0★ repoDecide whether and how to use TikTok Ads before anything gets built. Triggers on 'should I use TikTok Ads', 'what TikTok campaign objective should I run', 'plan my TikTok funnel', or 'TikTok Ads strategy for [business]'. Planning layer — hands off to tiktok-ads-campaign-builder for execution.
kalshamsi/fable-discipline-skills/skills/assumption-audit Skill
0★ repoBefore finalizing any analysis, recommendation, or decision made under incomplete information, surface the load-bearing assumptions, tag each as supported or unsupported by the given evidence, and stress-test the conclusion against the weakest one. Use this whenever you are asked "should we do X", to recommend or advise, to compare options, or to make strategy, hiring, budget, planning, prioritization, or operational judgment calls — even when the request doesn't mention assumptions or uncertainty. If the answer would rest on anything not directly stated in the given information, this skill applies.
kalshamsi/fable-discipline-skills/skills/plan-before-executing Skill
0★ repoFor any multi-step work, commit to an explicit ordered plan — steps, dependencies, and what done looks like — before producing the deliverable, then follow it and note deviations. Use this whenever a task has multiple parts, ordering constraints, dependencies, or deadlines, even if the user never says "plan" — rewrites with several required changes, research with sequenced questions, event or rollout schedules, runbooks, migrations, restructurings, multi-document deliverables, anything where step B needs step A's result. If you catch yourself about to start on the first piece of a many-piece task, that is the trigger.
kalshamsi/fable-discipline-skills/skills/rubric-self-check Skill
0★ repoExtract a request's explicit requirements into a checklist before drafting, then verify the draft against every item before delivering. Use this whenever a deliverable carries multiple explicit constraints — word or length limits, required sections or elements, mandated formats or templates, prohibitions, tone or audience rules — and for any detailed brief, spec, or compliance-sensitive output. Trigger on phrasings like "must include", "no more than", "exactly N", "in the format of", "do not mention", or any request that lists several requirements, even casually; if the request has three or more stated constraints, use this skill rather than trusting them to memory.
rabius-sunny/agent-skills/planning-and-task-breakdown Skill
no license0★ repoBreaks work into ordered tasks. Use when you have a spec or clear requirements and need to break work into implementable tasks. Use when a task feels too large to start, when you need to estimate scope, or when parallel work is possible.
The same file is in 4 other repositories
rabius-sunny/agent-skills/spec-driven-development Skill
no license0★ repoCreates specs before coding. Use when starting a new project, feature, or significant change and no specification exists yet. Use when requirements are unclear, ambiguous, or only exist as a vague idea.
The same file is in 3 other repositories
rabius-sunny/agent-skills/write-spec Skill
no license0★ repoWrite a feature spec or PRD from a problem statement or feature idea. Use when turning a vague idea or user request into a structured document, scoping a feature with goals and non-goals, defining success metrics and acceptance criteria, or breaking a big ask into a phased spec.
The same file is in 2 other repositories
muzalee/claude-atelier/skills/brief-to-tasks Skill
no license0★ repoBreak a design brief into an ordered checklist of independently buildable tasks using vertical slices. Saves as a markdown checklist. Use when user wants to break down work, create tasks from a brief, plan implementation order, or mentions "tasks" or "breakdown".
muzalee/claude-atelier/skills/design-brief Skill
no license0★ repoCreate a design brief through an interactive interview, codebase exploration, and experience design decisions. Saved as a markdown file in the project. Use when user wants to write a design brief, plan a new feature or page, define a UI direction, or mentions "brief".
muzalee/claude-atelier/skills/test-plan Skill
no license0★ repoWrite a short test plan for a change before implementing — list the cases that must pass, what to break to prove them, and what NOT to test. Use before starting non-trivial work, when asked for a "test plan", or when reviewing a PR to sanity-check coverage.
cobuchan/compounding-operator/skills/prd-creation Skill
0★ repoStandard format and workflow for creating PRDs with JSON stories. Includes schema, complexity rules, agent selection, and completion checklist. Use when creating product requirements, writing user stories, or planning feature work with structured tracking.
cobuchan/compounding-operator/skills/prd-stepper Skill
0★ repoExecute the NEXT (or a named) story in a PRD tracker file end-to-end — read the story spec from the JSON, mark in_progress, decide spawn-vs-inline based on complexity, run required gates, update the tracker with completed_date and implementation_notes. Companion to `prd-creation`. Use when the user says "continue with <story-id>", "next PRD story", "execute <story>", "step through the PRD", "what's next on the PRD", or "let's do the next one". This skill governs execution once a PRD tracker JSON exists, however it originated — whether created directly by `prd-creation` or handed off from some other planning process. Batching multiple PRD stories in one session, when the user opts in, is a legitimate variant of this same mechanism, not a different one.
rikocr8orh8/compliance-skills-previews/skills/video-strategy-extraction Skill
0★ repoTurn any expert walkthrough video into a structured, testable spec, using only what was actually said.
SkillMedev/nonprofit-grants-toolkit/skills/grant-proposal-writer Skill
0★ repoWrites the full foundation grant proposal for a nonprofit - need statement grounded in local data, a logic model with real numbers (inputs to activities to outputs to outcomes), SMART objectives, an evaluation plan sized to organizational capacity, a budget narrative where every line traces to an activity, and a credible sustainability answer. Use when a nonprofit leader says "write the full grant proposal", "we got invited to submit", "build our logic model", "our proposal needs an evaluation plan", or "the funder wants a budget narrative". Do NOT use for the initial one-page letter of inquiry - use grant-loi-writer instead - and do NOT use for corporate sales proposals - use sales-proposal-writer instead.
The same file is in 1 other repository
jpoindexter/brand-identity-skills/skills/clarifying-strategy Skill
no license0★ repoUse when defining what a brand stands for and what to call it — distilling research into a unifying idea, narrowing focus, writing a positioning strategy, developing a brand brief, running a naming project, or screening names for trademark/legal availability. Also when a merger, joint venture, blank-page startup, or repositioning needs a strategy or name.
jpoindexter/brand-identity-skills/skills/designing-identity Skill
no license0★ repoUse when starting Phase 3 creative design after the brand brief is agreed — designing the actual visual/sensory system: choosing wordmark vs symbol, building color palettes, selecting or commissioning typefaces, designing iconography, defining look and feel, adding sound/scent/touch/taste, testing marks in trial applications, or planning the first design presentation.
architshahdigital/claude-marketing-skills/skills/carousel-studio Skill
no license0★ repoPlan and write scroll-stopping social media carousels — concept, slide-by-slide copy, visual direction, and the caption — ready to hand to a designer or a design tool. Use when the user wants carousel ideas, needs to write carousel copy, is batching a month of carousels, or turning a content pillar into swipeable posts. Produces a structured carousel brief per concept. Triggers on: "carousel", "swipe post", "slide copy", "Instagram/LinkedIn carousel", "batch carousels", "content matrix".
kuotient/neel-nanda-skills/validation/first-draft-skill Skill
0★ repoProduce a rigorous, opinionated analysis of a claim, paper, proposal, design doc, argument, or idea — structured the way Neel Nanda writes research commentary: decompose the whole into functionally distinct claims, rate each on importance / confidence / standing separately, state a first-principles prior before weighing evidence, hunt the boring hypothesis behind every flattering result, and grade evidence on a spectrum instead of praising it uniformly. Use this whenever the user wants a considered opinion or review of something rather than a neutral summary — "이거 어떻게 생각해", "이 논문/제안서 평가해줘", "비평해줘", "내 의견을 정리하고 싶어", "review this", "what do you make of X", "is this claim convincing", "poke holes in this", or is reacting to a paper, RFC, strategy memo, or technical result and wants to know what to believe and how strongly. Prefer this over a plain summary any time the task is judgment, not description — even if the user doesn't name Neel Nanda.
NorthStar-Analytics-LTD/skill-foundry/skills/build-data-brief Skill
0★ repoSkill builder. Maps how data requests reach your team today, interviews whoever triages them, then generates a custom /data-brief skill that turns a vague business request into a decision-shaped brief before any analyst touches it — the decision it serves, the deadline, the owner, the definitions involved. Use when requests arrive as "can you pull some numbers" and half the team's time goes to clarifying instead of answering.
NorthStar-Analytics-LTD/skill-foundry/skills/northstar Skill
0★ repoThe NorthStar Method as a skill. Drops a forward-deployed analytics consultant into your repo: lands without a brief, senses the environment, makes a plan, executes in visible loops, fixes root causes, documents everything, and hands over cleanly. Use for any analytics problem area — a broken reporting estate, a migration, a data team drowning in support tickets, or "we don't trust our numbers". Give it a problem area and it owns it end-to-end. Calls the Foundry sub-skills when the problem matches one.
natexai2026/2030-skills/skills/scenario-branch Skill
0★ repoReplace a single point-forecast with 3–5 internally consistent futures built from named driver variables, each with triggering conditions, an ordinal plausibility, and how it propagates to other domains. Use whenever forecasting, planning under uncertainty, stress-testing a strategy, assessing risk, or answering "what will happen with X." Triggers on "what's the outlook for," "where is this heading," "will X happen by year N," roadmap and contingency planning, red-teaming a bet, and any question about the future where a single confident number would be a lie. Especially apt when the honest answer is "it forks."
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-blender/.claude/skills/blender-spec Skill
0★ repoTurn a vague modeling request ("make a chair") into a buildable, gradeable spec — subject and identity features, art direction, quality tier (hero by default), target use, real-world dimensions from reference or the archetype table, budgets, topology and material requirements, deliverables, and measurable done-criteria that blender-verify gates against. Use at the start of any Blender modeling task, before creating any geometry.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-blueprint/.claude/skills/design-doc Skill
0★ repoProduce a decision-complete design from a requirements register — codebase recon, 2-3 materially different architectures with trade-offs, failure-mode analysis, pinned interface contracts, cross-cutting concerns, ADRs, and a pre-mortem. Use after spec-interrogate's gate passes; output is docs/plan/<slug>/02-design.md.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-blueprint/.claude/skills/spec-interrogate Skill
0★ repoTurn a raw specification into a testable requirements register — hunt ambiguities, contradictions, gaps, and unstated non-functionals; triage open points into one batched round of user questions vs. recorded assumptions. Use immediately upon receiving any spec, PRD, or feature request; never design from a raw spec.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-blueprint/.claude/skills/ticketize Skill
0★ repoTurn a design into a risk-first milestone plan and executable tickets — walking skeleton, dependency graph, sized tickets with testable acceptance criteria, a forgotten-workstreams sweep, and a requirements-to-tickets traceability matrix. Use after design-doc's gate passes; output is docs/plan/<slug>/03-tickets.md.
nubasu/Pseudo-Fable-Framework/frameworks/pseudo-fable-lift/.claude/skills/deep-plan Skill
0★ repoPlan a non-trivial change before writing code — requirements contract, recon of the actual code, 2-3 materially different approaches, verifiable milestones, and a pre-mortem. Use when a task touches 3+ files, involves a design decision, or looks longer than ~30 minutes.
cozren/claude-code-setup/skills/quick-prd Skill
no license0★ repoCreates a structured Quick PRD (Product Requirements Document) from user-provided feature or product context. Use this skill whenever the user says "create quick PRD", "write quick PRD", or "quick PRD for X". Trigger even if the user only provides a rough feature idea or pastes some context — always use this skill to generate the PRD rather than winging it.
lightarktech/founder-coding-skills/skills/vertical-tickets Skill
0★ repoSlice work into thin end-to-end feature tickets, never into technical layers. Use when breaking any plan, spec, or feature request into workable units.
sumitake/agent-collab/plugins/agent-collab/skills/architect Skill
no license0★ repoUnified dynamic-host agent collaboration policy and signed-runtime client
SkillMedev/freelancer-consultant-os/skills/sales-proposal-writer Skill
0★ repoWrites a B2B sales proposal or SOW that restates the buyer's problem in their own words, quantifies the cost of inaction, presents price as anchored options, and drives one dated next step. Use when someone asks "write a proposal for this client", "turn my discovery notes into a proposal", "how should I present pricing in this proposal", or when a deal needs a document to move from discovery to close. Do NOT use for a one-page internal decision brief - use one-pager-designer instead; for investor decks use pitch-deck-builder; for setting the underlying price model use pricing-strategy.
The same file is in 3 other repositories
Giving-Back-Studio/growth-agent/skills/journal-strategic-planning Skill
no license0★ repoCreate and save a grounded Earth Care Network journal strategy for an enterprise. Use when someone wants a content strategy, editorial pillars, topic roadmap, publishing cadence, or a journal that supports sales without generic promotion.
Alterlab cdm festival strategy
prone-dc302/AlterLab-FC-Skills/skills/cdm/alterlab-cdm-festival-strategy Skill
0★ repoThis skill should be used when the user asks about "film festival", "festival submission", "logline", "synopsis writing", "director's statement", "festival strategy", "act as a festival strategist", "festival mode", "film submission", "short film festival", "festival circuit", "premiere strategy", "FilmFreeway", "Withoutabox", "press kit for film", or needs expertise in festival submission materials, loglines, synopses, director statements, and festival circuit planning. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
The same file is in 1 other repository
prone-dc302/AlterLab-FC-Skills/skills/cdm/alterlab-cdm-preproduction Skill
0★ repoThis skill should be used when the user asks about "pre-production", "shot list", "storyboard", "shooting schedule", "call sheet", "script breakdown", "scene breakdown", "production planning", "act as a pre-production planner", "pre-production mode", "location scouting", "crew planning", "shooting day schedule", "camera setup list", or needs expertise in pre-production planning, shot design, script breakdowns, and shooting logistics. Part of the AlterLab FC Skills collection (Cinema & Digital Media department).
The same file is in 1 other repository
Alterlab pra campaign strategist
prone-dc302/AlterLab-FC-Skills/skills/pra/alterlab-pra-campaign-strategist Skill
0★ repoThis skill should be used when the user asks about "campaign strategy", "IMC planning", "integrated marketing communications", "campaign architecture", "strategic brief", "ROSTIR model", "campaign plan", "act as a campaign strategist", "campaign strategist mode", "communication strategy", "campaign framework", "strategic planning for advertising", "RACE model", "PESO model", "media mix", "campaign evaluation", "campaign one-pager", "big idea", "campaign phasing", "campaign budget", or needs expertise in building full-scale integrated marketing communication campaigns from research to evaluation. Part of the AlterLab FC Skills collection (Public Relations & Advertising department).
The same file is in 1 other repository
prone-dc302/AlterLab-FC-Skills/skills/pra/alterlab-pra-creative-brief Skill
0★ repoThis skill should be used when the user asks about "creative brief", "communication brief", "single-minded proposition", "SMP", "one-page brief", "briefing the creative team", "writing a brief", "agency brief", "campaign brief", "act as a brief writer", "creative brief mode", "strategic brief", "key message development", "target audience brief", or needs expertise in writing concise, inspiring creative briefs that direct campaign development. Part of the AlterLab FC Skills collection (Public Relations & Advertising department).
The same file is in 1 other repository
prone-dc302/AlterLab-FC-Skills/skills/pra/alterlab-pra-media-planner Skill
0★ repoThis skill should be used when the user asks about "media planning", "media strategy", "media buying", "channel selection", "budget allocation", "CPM", "GRP", "reach and frequency", "media mix", "flighting schedule", "media flowchart", "act as a media planner", "media planner mode", "advertising spend", "media brief", or needs expertise in strategic media planning, channel selection, and budget optimization across paid media. Part of the AlterLab FC Skills collection (Public Relations & Advertising department).
The same file is in 1 other repository
prone-dc302/AlterLab-FC-Skills/skills/rma/alterlab-rma-proposal-writer Skill
0★ repoThis skill should be used when the user asks about "research proposal", "grant application", "funding proposal", "grant writing", "research justification", "proposal writing", "act as a proposal writer", "proposal writer mode", "ethics application", "IRB application", "ethics committee", "research budget", "budget planning", "research timeline", "Gantt chart", "proposal defense", "dissertation proposal", "thesis proposal", "research design", "methodology section", "literature gap", "significance of the study", "research objectives", "hypothesis formulation", "funding agency", "project narrative", "specific aims", or needs expertise in writing research proposals, grant applications, and ethics submissions. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
The same file is in 1 other repository
prone-dc302/AlterLab-FC-Skills/skills/rma/alterlab-rma-thesis-architect Skill
0★ repoThis skill should be used when the user asks about "thesis structure", "dissertation", "thesis writing", "chapter organization", "research proposal", "thesis outline", "defense preparation", "thesis defense", "committee management", "thesis timeline", "writing productivity", "argument architecture", "thesis introduction", "literature review structure", "methodology chapter", "findings chapter", "discussion chapter", "thesis conclusion", "act as a thesis architect", "thesis architect mode", "dissertation proposal", "thesis pipeline", "academic writing structure", "thesis formatting", "thesis revision", "writing schedule", "thesis advisor", "research proposal writing", "thesis planning", "chapter drafting", "thesis feedback", "defense slides", "viva preparation", or needs expertise in structuring, planning, writing, and defending a thesis or dissertation. Part of the AlterLab FC Skills collection (Research Methods & Academic Writing department).
The same file is in 1 other repository
supermodo/skills/skills/grill Skill
0★ repoTwin-agent adversarial interview that locks a task or design before implementation. Two models plan independently, attack each other's plans, and only genuinely user-owned questions reach you — the locked outcome is handed to librarian to write. Use for 'grill', 'grill me', plan stress-test, design interview, new-task intake, spec lock, or a flow `needs-input` escalation.
tamasbege/staff-engineer-skills/plugins/staff-engineer-skills/skills/caching-strategy-architect Skill
0★ repoDesign caching architectures that are fast AND correct - cache placement (in-process, distributed, CDN), pattern selection (cache-aside, read-through, write-through, write-behind), TTL and invalidation strategy, stampede protection, and consistency guarantees. Use when database load is too high, latency needs cutting, the same data is fetched repeatedly, users see stale data after updates, cache and database disagree, a cache expiry causes load spikes (thundering herd), or the user asks where or how to add caching or fix cache invalidation.
YasuakiOmokawa/skills/plugins/create-design-doc/skills/create-design-doc Skill
0★ repoプロトタイプと案件プランファイルの申し送り節から DD (Design Doc) を作成するときに使用。「DD を作って」「デザインドックを起こして」「設計書にして」で起動。テンプレートは ~/.claude/skills-config/create-design-doc/dd_template.md を参照し、未配置なら「テンプレートなしで作成」と宣言して進める。
YasuakiOmokawa/skills/plugins/define-acceptance-criteria/skills/define-acceptance-criteria Skill
0★ repoFills a matrix of 3 required categories (normal, error, edge) by controlled-vocabulary perspectives to enumerate acceptance criteria and technical risks into the analysis file, then appends a one-line summary to the plan file. Use when in plan mode before /mece-plan-review, when the user asks to write AC for a plan ("受け入れ条件を定義して" / "AC を書いて"), when an AC matrix is needed as MECE input, or when delegated to a subagent (Task tool) for the same purpose. Not typically invoked during PoC / throwaway-validation phases (the assumption ledger substitutes there).
YasuakiOmokawa/skills/plugins/dry-ssot-text/skills/dry-ssot-text Skill
0★ repoCollapses repeated explanations of one concept into a single source of truth plus cross-references, while keeping navigation aids like TOCs and progress tables. Use when an AI-generated document (plan / design doc / RFC / PR description) has grown long with the same concept explained in multiple places, when the same why-explanation is repeated across multiple code comments, or when the user says "この文書の重複をまとめて" / "この文書を DRY にして" / "同じ説明が何回も出てくるので整理して". Also use when a change set spans multiple files (code comments + changed/new docs) with the same explanation duplicated across them. Prose duplication inside code comments is in scope; code structure duplication / refactoring is out of scope.
YasuakiOmokawa/skills/plugins/extract-figma-spec/skills/extract-figma-spec Skill
0★ repoFigma デザインをコードへ反映・適用する実装の前後、figma-dev-mode MCP で design-to-code を行うとき、または「Figma 通りに実装して」「デザインを反映して」「Figma の指定どおりに直して」と頼まれたときに使用。スクショ目視と人間が挙げた「指定 N 点」だけで反映すると、hex の微差・font weight(Bold)・アイコンや枠の有無・要素まるごとの欠落 といった Figma 指定を取りこぼす——この反映漏れ (デザイン崩れ・Figma 不一致) を防ぐ。差分は通常 /define-acceptance-criteria で AC 化し /qa-ui で検証する(PoC 等の使い捨て検証では省略可)。チェックリスト全行は atom ID 付きで `## 正本抽出結果` として分析ファイルに書き出し、/finalize-plan の正本カバレッジ・ゲートの入力になる。
YasuakiOmokawa/skills/plugins/finalize-plan/skills/finalize-plan Skill
0★ repoAgent skills for improve AI driven development
YasuakiOmokawa/skills/plugins/map-user-stories/skills/map-user-stories Skill
0★ repo設計書・プロジェクト仕様・Jira epic等からユーザーストーリーマップを作成し、タスク分解・スプリント計画まで行う場合に使用。新しいプロジェクトフェーズの計画、設計書の分析、大きな機能の実装単位への分解が必要な場合にトリガーされる。対象の設計書は DD がレビュー確定した後を想定する。
YasuakiOmokawa/skills/plugins/mece-plan-review/skills/mece-plan-review Skill
0★ repoVerifies acceptance criteria for MECE coverage with spec (BB) and code (WB) perspectives — run inline by the main agent by default, with a fresh red-team judge dispatched only when critical candidates emerge; risk domains (auth/billing/payment/migration) or >15 AC escalate to deep tier (parallel BB/WB subagents + mandatory red team), and the Devin wiki researcher joins only on explicit user opt-in. Records coverage gaps and duplicates in the analysis file. Use when AC is already defined in the analysis file via /define-acceptance-criteria and MECE verification is required before implementation, or when the user says "AC の網羅性を検証して" / "MECE 検証して". Not typically invoked during PoC / throwaway-validation phases (the assumption ledger substitutes there).
YasuakiOmokawa/skills/plugins/purge-private-vocab/skills/purge-private-vocab Skill
0★ repoDetects local-plan coinages, abbreviations, and number labels in reader-facing text and rewrites them so readers without the source plan can follow. Use after generating PR description, Jira ticket, design doc, RFC, reviewed code comments (plan-coinage residue left after implementation), or other reader-facing text from a local plan/spec file, when readers don't share the source plan, when a plan document itself must be checked because upstream analysis-file finding IDs (BB-N / WB-N / IM-N) leaked into it, or when the user says "造語チェックして" / "plan 用語を消して" / "PR 説明の語彙を点検して".
YasuakiOmokawa/skills/plugins/review-plan-diff/skills/review-plan-diff Skill
0★ repo実装完了後に、確定プラン (finalize-plan 出力)、または DD 該当タスクを転記した簡易プランと実装後の diff を突き合わせ、実装漏れ・仕様逸脱・計画外差異を検出したいときに使用する。「プランと突き合わせて」「実装漏れがないか見て」「diffがプラン通りか確認して」等の依頼で起動する。
KARIMMOHAMED2729/critical-briefs/skills/critical-process-brief Skill
0★ repoCreate critical process briefs through challenging dialogue that exposes operational blind spots and stress-tests workflows. Use when user wants to map out business processes, operations, or workflows. Proactively finds gaps, exposes hidden complexity, identifies fragile points, and tests scalability. Creates structured process briefs in .ideas/[name]/process.md. Triggers include "how would this work operationally", "what's the process", "how do we deliver", or operational details questions.
gabriel-f-santos/coding-agents/skills/plan-phase Skill
no license0★ repoGenerate a technical implementation plan for a project phase. Use whenever the user asks to plan, detail, or generate the technical plan for a phase — including variations like 'plan phase X', 'detail the phase', 'generate phase implementation', 'create the phase-XX.md', or any mention of creating the technical document for a project phase.
gabriel-f-santos/coding-agents/skills/prd-creator Skill
no license0★ repoDraft a Product Requirements Document that feeds the plan→execute pipeline. Use whenever the user wants to write, draft, or scope a PRD, spec out a feature/module/migration before building, or 'criar um PRD', 'escrever o PRD de X', 'spec dessa feature', 'documentar o que vamos construir'. Produces docs/prd-<slug>.md in the repo's house format — grounded in the real codebase — with the slug that carries through /research and /plan-phase. It is the front door of the pipeline: PRD → /research → /plan-phase → /implement-phase. Do not use to write the technical decisions (use /research) or the phase breakdown (use /plan-phase).
gabriel-f-santos/coding-agents/skills/product-discovery Skill
no license0★ repoTurn a vague product idea into a validated discovery brief through a deep founder interview, live market research, and generated user-research instruments. Use when the user has a product/SaaS/feature idea and wants to validate the problem before building — "tenho uma ideia", "quero validar um produto", "product discovery", "pesquisa de mercado", "vamos descobrir se vale a pena", "monta uma entrevista/survey pros usuários", "TAM SAM SOM". It interviews the founder (Mom Test + JTBD framing), researches the market (TAM/SAM/SOM, competitors, demand signals) using parallel subagents when available, generates user-research instruments (interview guide, survey, screener, fake-door landing), and writes a discovery brief. Do not use to write a build spec/PRD (that comes after) or to brainstorm features without validation — use product-brainstorming for pure ideation.
gabriel-f-santos/coding-agents/skills/tech-discovery Skill
no license0★ repoAct as a senior technical architect running technical discovery AFTER product discovery/brainstorming. Use when a problem/product is validated and you need to design the system before building — "discovery técnico", "arquitetura da solução", "como vamos construir isso", "desenho de sistema", "technical discovery", "solution architecture", "definir a arquitetura". Reads the product discovery brief/PRD, explores architecture options with trade-offs, designs boundaries (C4/DDD), the data model, NFRs + cost, and a STRIDE threat model, surfaces the riskiest unknowns as time-boxed spikes, and writes a Tech Discovery Brief that feeds prd-creator and research. Do not use for product/market discovery (use product-discovery), for granular lib/pattern choices per phase (use research), or for the implementation plan (use plan-phase).