Plan & spec
10,699 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
yuanyuanyuan430/ganhuo-ai-growth-skills/skills/ganhuo-search-intent-brief Skill
0★ repoConvert keywords into search-intent analysis and SEO content briefs by inspecting SERP page types, user jobs, content formats, required modules, and mismatch risks. Use when keywords are not ranking, one page targets multiple intents, content briefs are needed, or Codex must decide whether a query needs a product page, article, tool, UGC page, video, comparison, or glossary.
NyXXiR/skillboard/examples/multi-source-skills/omo/ulw-plan Skill
0★ repoPlan complex work in a LazyCodex harness.
NyXXiR/skillboard/examples/skills/requirement-intake Skill
0★ repoRoute vague feature requests into clear requirements, open questions, and implementation-ready scope.
yogeshg665/quill-trading-agent/skills/dca-strategy Skill
0★ repoSpread a fixed periodic contribution evenly across a watchlist as whole-share buys, independent of short-term signals. WHEN: "dollar cost average", "DCA into my watchlist", "invest my weekly contribution", "steady accumulation", "scheduled buys", "spread my deposit across names".
yogeshg665/quill-trading-agent/skills/mean-reversion-strategy Skill
0★ repoFade statistical extremes by buying oversold names and exiting overbought ones using a close-price z-score. WHEN: "buy the dip", "mean reversion trade", "this is oversold", "fade the spike", "revert to the mean", "z-score signal".
yogeshg665/quill-trading-agent/skills/momentum-strategy Skill
0★ repoFollow strong price trends by buying names with high trailing returns and exiting positions that have rolled over. WHEN: "buy the trend", "momentum trade", "follow strong movers", "this stock is breaking out", "exit the downtrend", "trend-following proposal".
yogeshg665/quill-trading-agent/skills/rebalancing-strategy Skill
0★ repoPropose trades that move the portfolio back toward its target weights when a holding drifts beyond the tolerance band. WHEN: "rebalance my portfolio", "drift back to target", "my weights are off", "bring positions to target allocation", "trim overweight and add underweight".
yogeshg665/quill-trading-agent/skills/relative-strength-strategy Skill
0★ repoTrade US equities by their strength relative to the benchmark (SPY). Buy names that outperform the index over the lookback window and exit held names that lag, suppressing new buys in a risk-off regime. WHEN: "relative strength", "outperforming the S&P", "beating SPY", "leaders vs laggards", "buy the market leaders", "exit the laggards", "alpha vs benchmark".
yogeshg665/quill-trading-agent/skills/thematic-strategy Skill
0★ repoBuild initial exposure to conviction themes by adding new names in a target sector that are not yet held. WHEN: "invest in this theme", "add exposure to a sector", "build a position in healthcare", "thematic tilt", "buy names in my theme", "start a thematic basket".
lensetek/BrevetAB-Agent-Skills/skills/tax-planner-strategist Skill
0★ repoMenyusun strategi tax planning yang legal, melakukan simulasi efisiensi pajak PPh Badan/OP, dan meminimalkan biaya pajak tanpa melanggar undang-undang (tax avoidance).
Sarmkadan/dotnet-senior-skills/skills/exception-and-result-strategy Skill
0★ repoDecide when C# code should throw, when to return a Result type, what exceptions to define, and what must never be swallowed. Use when reviewing error handling, try/catch blocks, or designing failure contracts for services and APIs.
Sarmkadan/dotnet-senior-skills/skills/testing-strategy Skill
0★ repoDecide what to test at each layer of a .NET service, when integration tests beat unit tests, why mocking DbContext is a smell, and what makes tests worth their maintenance cost. Use when writing tests, reviewing test PRs, or designing a test suite.
Tsurai7/agentic-playbook/skills/model-orchestration Skill
0★ repoRoute each sub-task to the cheapest model tier that can do it well, and delegate execution to subagents. Apply when planning a multi-step or token-expensive task, choosing between strong/mid/cheap models (Opus/Sonnet/Haiku), or deciding whether to spawn subagents. Plan and decide with a strong model; execute well-specified sub-tasks with a cheap one; escalate on failure. Skip for a single trivial step - orchestration has overhead. Prompt/cache token costs of an LLM system belong to prompt-caching-playbook.
Tsurai7/agentic-playbook/skills/office-hours Skill
0★ repoPressure-test an idea before building it - premise challenge, status quo, evidence of value, narrowest wedge, risk, cost of keeping. Use when asked to vet/scope a proposal, decide whether something is worth adding ("стоит ли внедрять X"), or before writing an implementation plan for a new capability. Skip for bug fixes with an obvious cause and for work already scoped by an accepted plan.
Tsurai7/agentic-playbook/skills/plan-review Skill
0★ repoEngineering review of an implementation plan before any code is written: scope challenge first, then architecture, code quality, tests, performance. Use when asked to review/critique a plan, design doc, or proposed approach, or before approving a multi-file implementation plan. Skip for reviewing a code diff (staff-review), for deciding whether the idea is worth building at all (office-hours), and for single-step plans with an obvious shape.
bingelp/skills/skills/grill-with-docs Skill
no license0★ repoA relentless interview to sharpen a plan or design, which also creates docs (ADRs and glossary) as we go. Use when the user wants to stress-test a plan or design before committing to it, outside the normal /spec or /plan flow.
bingelp/skills/skills/plan Skill
no license0★ repoTurns an approved spec into a technical plan and task breakdown. Only runs when the user explicitly types /plan.
bingelp/skills/skills/review Skill
no license0★ repoFinal spec-conformance review comparing the implementation against specs/<slug>/spec.md and plan.md. Only runs when the user explicitly types /review.
bingelp/skills/skills/spec Skill
no license0★ repoWrites a spec for a new feature or significant change. Only runs when the user explicitly types /spec.
bingelp/skills/skills/tally Skill
no license0★ repoReports the per-step and total token/USD cost of a feature by attributing past session transcripts to its spec → plan → build → test → review → ship steps. Only runs when the user explicitly types /tally.
bingelp/skills/skills/where Skill
no license0★ repoReports where a feature stands in the spec → plan → build → test → review pipeline by inspecting specs/<slug>/. Only runs when the user explicitly types /where.
getpipher/skills/skills/workspace/skills/planning-sync Skill
0★ repoAnalyze repo and provide intelligent planning documentation suggestions (read-only)
tony-adamson/groundwork-bench/vendor/skills/solution-design Skill
no license0★ repoUse when explicitly asked for $solution-design to create SOLUTION.md for one concrete software change before implementation planning. Produces a minimal evidence-based design; does not write code or create an implementation plan.
The same file is in 1 other repository
aneviaro/pipack/agent/skills/plan-linked-review Skill
no license0★ repoReview current local changes for correctness, quality, and best practices against a required implementation plan link or path. Use when asked to review local changes, diffs, or implementation progress against a plan/spec step. If no plan link/path is provided, use ask_user_question before reviewing.
Pdbjork/hermosskills-site/skills/ce-brainstorm Skill
no license0★ repoExplore vague or ambitious ideas into a right-sized requirements-only unified plan. Use when the user wants to brainstorm, think through scope, decide what to build, or needs collaborative product framing before planning.
Pdbjork/hermosskills-site/skills/ce-plan Skill
no license0★ repoCreate structured plans for multi-step work, including software and non-software tasks. Use when asked to plan, break down implementation, plan from requirements, or deepen an existing plan; prefer ce-brainstorm for exploratory framing.
Pdbjork/hermosskills-site/skills/ce-strategy Skill
no license0★ repoCreate or update STRATEGY.md. Use when starting a product, changing direction or roadmap, or when ce-ideate, ce-brainstorm, or ce-plan need upstream product grounding.
The same file is in 1 other repository
Pdbjork/hermosskills-site/skills/ce-work Skill
no license0★ repoExecute a plan or concrete work prompt end-to-end. Use when implementing from docs/plans, a spec path, or a clear build request; use ce-debug for open-ended bugs.
The same file is in 1 other repository
Pdbjork/hermosskills-site/skills/ecc-product-capability Skill
no license0★ repoTranslate PRD intent, roadmap asks, or product discussions into an implementation-ready capability plan that exposes constraints, invariants, interfaces, and unresolved decisions before multi-service work starts. Use when the user needs an ECC-native PRD-to-SRS lane instead of vague planning prose.
The same file is in 1 other repository
HeyEddi-com/skills/skills/design-handoff-flutter Skill
0★ repoImplements Flutter screens from designer screenshots and handoff notes using Material 3. Two-pass workflow: mockup-brief with Implementation spec, then AppShell + route screens. Use when approved mockups exist for a HeyEddi Flutter app.
HeyEddi-com/skills/skills/heyeddi-handoff Skill
0★ repoImplements screens from designer screenshots and handoff notes. Two-pass workflow: designer writes mockup-brief with Implementation spec, implementer builds shell then route, verify_handoff checks tokens and layout. Use when approved mockups exist: not for greenfield design.
HeyEddi-com/skills/skills/heyeddi-product Skill
0★ repoProduct leadership: user stories, acceptance criteria, backlog, holistic reviews. Verifies the product works and is useful; delegates UX flow, design critique, visual contrast, and engineering audits; synthesizes plans and change recommendations. Use after @heyeddi-intake, before ship, or when the user asks for PM review, user stories, acceptance criteria, or "is this feature good enough?"
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/design-handoff-flutter-settings/.agents/skills/design-handoff-flutter Skill
0★ repoImplements Flutter screens from designer screenshots and handoff notes using Material 3. Two-pass workflow — mockup-brief with Implementation spec, then AppShell + route screens. Use when approved mockups exist for a HeyEddi Flutter app.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/design-handoff-flutter-settings/.cursor/skills/design-handoff-flutter Skill
0★ repoImplements Flutter screens from designer screenshots and handoff notes using Material 3. Two-pass workflow — mockup-brief with Implementation spec, then AppShell + route screens. Use when approved mockups exist for a HeyEddi Flutter app.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/design-handoff-only/.agents/skills/design-handoff Skill
0★ repoImplements screens from designer screenshots and handoff notes. Two-pass workflow — designer writes mockup-brief with Implementation spec, implementer builds shell then route, verify_handoff checks tokens and layout. Use when approved mockups exist — not for greenfield design.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/design-handoff-only/.cursor/skills/design-handoff Skill
0★ repoImplements screens from designer screenshots and handoff notes. Two-pass workflow — designer writes mockup-brief with Implementation spec, implementer builds shell then route, verify_handoff checks tokens and layout. Use when approved mockups exist — not for greenfield design.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.agents/skills/design-handoff Skill
0★ repoImplements screens from designer screenshots and handoff notes. Two-pass workflow — designer writes mockup-brief with Implementation spec, implementer builds shell then route, verify_handoff checks tokens and layout. Use when approved mockups exist — not for greenfield design.
HeyEddi-com/skills/evals/runs/2026-07-04T22-58-59Z/full-product-integration/.cursor/skills/design-handoff Skill
0★ repoImplements screens from designer screenshots and handoff notes. Two-pass workflow — designer writes mockup-brief with Implementation spec, implementer builds shell then route, verify_handoff checks tokens and layout. Use when approved mockups exist — not for greenfield design.
ZC0325/sol-native-guardrails/plugins/sol-native-guardrails/skills/testing-strategy Skill
0★ repoChoose proportionate tests when the validation approach is a material engineering decision, such as critical behavior, regressions, weak or expensive test harnesses, cross-system integrations, or meaningful tradeoffs between strict test-first, targeted automation, and visual or manual evidence. Do not use for routine changes with an obvious existing test path.
blaze10011/market-flow-desk/.claude/skills/structural-levels Skill
no license0★ repoStructural support/resistance — swing pivots, unfilled gaps, and key moving averages the market actually made, with distance in % and ATRs. Use when the user asks "where's support on X?", "where should my stop go?", "what's the next resistance?", "key levels for X", or as part of analyzing the daily brief so every lean's level is anchored to structure instead of a naked ATR multiple. Feeds the technical-analysis trade plan too.
angpysha/api2skill/.agents/skills/grill-with-docs Skill
0★ repoRelentless interview to sharpen a plan or design. All resolved information is written via Spec Kit (/speckit.* → spec.md/plan.md). Glossary (CONTEXT.md) and ADRs supplement only. Composes grilling + domain-modeling + spec-kit.
angpysha/api2skill/.agents/skills/spec-kit Skill
0★ repoSpec-Driven Development backbone via GitHub Spec Kit (specify CLI + /speckit.* commands). Every SDLC phase drives the matching /speckit command; spec.md/plan.md/tasks.md are the machine-checkable source of truth. Use during install/adapt (constitution) and every phase.
angpysha/api2skill/.agents/skills/speckit-analyze Skill
0★ repoPerform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
angpysha/api2skill/.agents/skills/speckit-converge Skill
0★ repoAssess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
angpysha/api2skill/.agents/skills/speckit-plan Skill
0★ repoExecute the implementation planning workflow using the plan template to generate design artifacts.
angpysha/api2skill/src/Api2Skill/templates/api2skill-creator Skill
0★ repoInterview the user about an OpenAPI/Swagger API (including multi-spec, base URL, and authorization), assemble exact api2skill CLI commands, then guide secrets.json setup from secrets.example.json placeholders. Prefer Plan mode for multi-spec interviews.
ohyesgocool/feature-loop/skills/plan-feature Skill
0★ repoLoop engineering for AI coding agents: plan → build → MR → independent AI review → fix → re-review until clean, with a merge gate and a self-learning blind-spot ledger. Agent Skills format, Claude Code native, MIT.
ohyesgocool/feature-loop/skills/ship-feature Skill
0★ repoLoop engineering for AI coding agents: plan → build → MR → independent AI review → fix → re-review until clean, with a merge gate and a self-learning blind-spot ledger. Agent Skills format, Claude Code native, MIT.
victorgrein/victorgrein-skills/engineering/to-spec Skill
no license0★ repoTurn explicitly designated input documents into an approved implementation spec in a per-spec folder under .context/specs. Use when the user explicitly invokes $to-spec with local or attached documents, documentation URLs, or pasted Markdown and wants uncertainties resolved through a one-question-at-a-time interview before the spec is written.
incuca/incuca-ads/skills/ads-plan Skill
0★ repoStrategic paid advertising planning with industry-specific templates. Covers platform selection, campaign architecture, budget planning, creative strategy, and phased implementation roadmap. Use when user says ad plan, ad strategy, campaign planning, media plan, PPC strategy, or advertising plan.
k97/skills/skills/stage-gate Skill
0★ repoQuality gates for the three checkpoints of a feature cycle: after planning (--plan gates the plan for unstated assumptions and unverifiable success criteria), after development (--dev reviews the diff for overcomplication and non-surgical changes), and after merge or release (--release captures lessons into rules and keeps the agent memory file lean via progressive disclosure). Agent-agnostic: targets CLAUDE.md, AGENTS.md, GEMINI.md, or Copilot instructions — Claude Code, Codex, Cursor, Copilot, Gemini CLI, Antigravity. --release also bootstraps a new repo: creates the memory file if missing, prunes init-generated bloat. Use for "review my plan", "gate this diff", "is this overcomplicated", "post-merge hygiene", "capture lessons", "CLAUDE.md is too long", "AGENTS.md is too long", "set up CLAUDE.md for this repo". Scope with --plan, --dev, --release.
vaibhavsaxena022/skills/caching-strategy Skill
0★ repoAdd caching to a read-heavy path with a correct invalidation strategy. Use when an endpoint or query is read-heavy and slow. Chooses what to cache, where, the TTL, and how to keep it from going stale.
vaibhavsaxena022/skills/plan-first Skill
0★ repoProduce a plan and get alignment BEFORE writing any code. Use when the task is non-trivial or ambiguous, or the user says "plan this", "how would you do X", or "don't code yet". Explores, proposes an approach with tradeoffs, and stops for approval — no implementation until asked.
grimoire-rs/grimoire-vscode/.claude/skills/swarm-plan Skill
0★ repoUse for feature planning, task decomposition, multi-perspective research, or ADR scaffolding. Tier (`low | auto | high | max`) scales research depth, architect model, and review breadth. Canonical research primitive for AI config / ADR work.
SamyakJhaveri/loam/cultivation/marketplace/planning-with-files/skills/planning-with-files Skill
0★ repoManus-style persistent markdown planning with task_plan.md, findings.md, progress.md. Hook-based re-injection after /compact.
SamyakJhaveri/loam/cultivation/marketplace/pocock-engineering/skills/to-issues Skill
0★ repoBreak a plan, spec, or PRD into independently-grabbable issues on the project issue tracker using tracer-bullet vertical slices. Use when user wants to convert a plan into issues, create implementation tickets, or break down work into issues.
SamyakJhaveri/loam/cultivation/marketplace/pocock-engineering/skills/to-prd Skill
0★ repoTurn the current conversation context into a PRD and publish it to the project issue tracker. Use when user wants to create a PRD from the current context.
SamyakJhaveri/loam/seed/.claude/skills/gen-spec Skill
0★ repoGuided specification generation wizard. Use when adding a new feature, API endpoint, or component — forces a written spec before implementation. Validates scope, drafts a structured spec, checks it against conventions, and registers it in the project. NOT for: single-file bug fixes, refactors with no new behavior, or documentation-only changes.
SamyakJhaveri/loam/seed/.claude/skills/plan-review-invoke Skill
0★ repoInvoke the plan-reviewer agent using the canonical reference prompt from seed/plan-reviewer-design.md. Use when reviewing a plan in a fresh Claude Code session (after the plan was created in a prior session) and you want adversarial review (checklist + Elegance Gate + handoff plan) without manually copy-pasting the reference prompt. Accepts the plan path as an argument. NOT for: same-session plan reviews (just invoke the agent directly with the plan in context), reviewing implementations that already shipped (use /multi-review or /session-critique), or spec audits (the agent has a separate Spec Audit mode invoked differently).
ats4321/claude-engineering-skills/skills/campaign-planning Skill
0★ repoDecompose and execute large multi-step engineering efforts — multi-file features, migrations, and multi-agent workstreams. Auto-load when a task spans many files/days/agents, when planning a migration or rollout, when coordinating parallel subagents or engineers, when a big effort has stalled half-done, or when delegating slices of work with expectations of unattended execution. Covers risk-first slicing, per-slice done-criteria, dependency ordering, checkpoints that keep the system working, parallelization rules, delegation contracts, and pre-planned failure recovery. NOT for single-slice tasks (just do them) and NOT for the design itself (system-design).