Explore skills
Search every indexed skill by name, description, repository or instructions, then narrow the results.
Showing 57001–57030 of 57671 skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| discovery-upsert-hypothesis-canvastsunami28/MindNovaCapture a product hypothesis (lean canvas) for a discovery theme so discovery stays evidence-driven, not opinion-driven. Use when a discovery direction needs framing before work proceeds: phrasings like "what's our hypothesis here", "frame this as a hypothesis", "write a lean canvas", "what are we assuming", "what's the riskiest assumption", "how would we validate this", "is this a fact or a guess", or when research has surfaced a belief that should be stated and tested. Do NOT use to synthesise raw research (that is discovery-synthesize-research), to write a full PRD or map stories (that is elaboration-upsert-prd-document / elaboration-upsert-user-story), or to author an ADR (governance-author-adr). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| elaboration-upsert-api-contracttsunami28/MindNovaProduce a machine-readable API specification (OpenAPI 3.x in YAML) for the slice being built, so the build and tests consume a contract instead of prose. Use when designing or changing a REST endpoint, when the user says "design the API for this", "write the OpenAPI spec", "define the contract for MN-42", "what should the request/response shape be", or before code generation begins on a slice that exposes or changes an HTTP surface. This is the L3 keystone: the contract lives in the repo. Do NOT use to author an ADR (that is governance-author-adr), to write feature docs, to generate the implementation (that is create-code-generation), or for non-HTTP work. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| elaboration-upsert-prd-documenttsunami28/MindNovaWrite a Product Requirements Document for an initiative or epic - the problem, goals, scope, requirements, and success metrics - as the elaboration-phase anchor that stories derive from. Use when an initiative needs framing before it is sliced into work: phrasings like "write a PRD", "draft the product requirements", "what are the requirements for this epic", "spec out this initiative", "what's in and out of scope", "define success for MN-10", or when a confirmed hypothesis is ready to become a buildable epic. Do NOT use to capture an early hypothesis (that is discovery-upsert-hypothesis-canvas), to slice a PRD into stories (elaboration-upsert-user-story), to design the API contract (elaboration-upsert-api-contract), or to author an ADR (governance-author-adr). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| elaboration-upsert-user-storytsunami28/MindNovaCreate or draft new work items (stories, tasks, bugs, epics) as local markdown files under docs/discovery/, following the house story template, point scale, and conventions. Use this whenever the user wants a new work item: phrasings like "create" or "write up a story", "make a ticket", "log a bug" or "ops task", "create an epic", "raise a ticket", or any description of work that should be tracked as a new item, even when they only describe the work rather than naming a ticket. Do NOT use this for reading, searching, commenting on, transitioning, or reviewing existing tickets; for GitHub issues or pull items, GitHub issues or pull requests, Confluence pages, or PRDs; or for a bare "what points would you give" estimate when there is no ticket to create. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| elaboration-upsert-user-story-acceptance-criteriatsunami28/MindNovaDerive clear, testable acceptance criteria for a story and define the test-trait mapping that lets the deferred AC-coverage gate attach with no rework. Use when the user says "write the acceptance criteria", "define the ACs for MN-42", "what are the success criteria for this story", "make these criteria testable", "turn this story into checkable conditions", or "set up the AC-to-test mapping" - and when a story is being refined for build but its success criteria are vague or untestable. Do NOT use to CREATE the story (that is elaboration-upsert-user-story), to implement or tag the tests (that is create-code-generation), or to write the work item fields directly (defer that to governance-enrich-ticket). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| governance-author-adrtsunami28/MindNovaSuggest and author Architecture Decision Records (MADR-style) in docs/adrs/. Use when a load-bearing decision is being made or has just been made ("we decided to...", "let's go with X over Y", "should this be an ADR?", "record this decision", "write an ADR", "supersede ADR NNNN"), or when reviewing a plan/change that implies an unrecorded architectural choice. Also use to detect and flag decisions that ought to be recorded. Do NOT use for the project-wide constitution (that is the governance-constitution skill), for ordinary feature docs, or for tracker tickets. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| governance-check-graphtsunami28/MindNovaValidate documentation and graph integrity across the repo: the AI-SDLC artifact graph (every artifact declaring a `story:` has a valid work-item key, a known phase, and `relates:` links that resolve) AND the documentation wiki (no orphan pages, no broken relative links, indexes in sync), and documentation house-style (no em-dash characters). Use when the user says "check the artifact graph", "validate the artifact links", "lint the docs", "are the doc links broken", "check the wiki", "check for em-dashes", before opening a PR that touches docs or graph artifacts, or as the governance-check-graph step. It runs the same scripts the CI gates run, so local results match the pipeline. Do NOT use to create or fix artifacts, tickets, links, or docs (that is elaboration-upsert-user-story / governance-enrich-ticket / governance-author-adr / create-upsert-documentation). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| governance-constitutiontsunami28/MindNovaCreate, amend, or check a project's governing "constitution" - the small set of non-negotiable engineering principles that every agent run (Claude Code and GitHub Copilot) should honour. Use when the user says "create/set up a constitution", "add a rule/principle to the constitution", "amend/update the constitution", "make this a non-negotiable", "what are our project principles", or asks to bootstrap the AGENTS.md contract; and in check mode when the user says "check my changes against the constitution", "does this violate a clause", "constitution check", or "review this for constitution compliance". Do NOT use for authoring a single architectural decision (that is governance-author-adr), for validating doc or graph link integrity (that is governance-check-graph), for ordinary docs, or for editing tracker tickets. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| governance-enrich-tickettsunami28/MindNovaUpdate an existing local work item (under docs/discovery/) so its content reflects current reality after work ships or scope changes: splice shipped behavior, decisions, and approach into the matching section, fix a stale title, add related-item links with the reason for each, and backlink ADRs, designs, and docs. Use when the user says "add this to MN-42", "enrich MN-42", "the ticket should say what we actually shipped", "update the description to match reality", "link these items and say why", "record this decision on the story", or finishes work that changed what the story is or produced an artifact worth recording. Invoking it is a directive to WRITE the file after one confirmation, not to leave a proposal. Do NOT use to CREATE a work item (that is elaboration-upsert-user-story) or to read or search items. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| governance-validate-skillstsunami28/MindNovaValidate the AI-SDLC skills under .claude/skills/ with the layered eval harness before relying on a new or changed one. Use when a skill has just been added or edited and needs checking, or when the user says "eval the skills", "validate this skill", "run the skill harness", "test the skills", "did my skill change break routing", or "check skill discriminability". This is the durable form of the "draft-only eval harness" the roadmap refers to. Do NOT use to validate the artifact graph or docs wiki (that is governance-check-graph), or to author or edit a skill's content. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| mature-analyze-tickettsunami28/MindNovaTriage an incoming work item (under docs/discovery/) - a bug report, request, or incident - so it is correctly understood, classified, and routed before anyone builds. Use when the user says "triage MN-42", "is this a real bug?", "can you reproduce this?", "what priority is this", "is this a duplicate", "look into this report/incident", or hands you an inbound item to assess. Reads the item and its evidence, reproduces or characterises the problem, classifies and prioritises it, checks for duplicates, and records a triage note. Do NOT use to CREATE an item (that is elaboration-upsert-user-story), to rewrite an item's content (that is governance-enrich-ticket), or to implement the fix (that is mature-resolve-ticket). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| mature-collect-release-feedbacktsunami28/MindNovaGather post-release signals and record them as concise feedback notes anchored on the originating epic/story. Use after a release ships and you need to learn whether it delivered its intended outcome: phrasings like "did the release land", "collect feedback on what we shipped", "what is the telemetry showing for this feature", "summarise the support tickets since release", "what did stakeholders say", or when a feature is in production and should feed the next loop. This is the entry point to the mature phase. Do NOT use to triage a specific issue the feedback surfaced (that is mature-analyze-ticket), to turn validated needs into new stories (that is elaboration-upsert-user-story), to run fresh research (that is discovery-synthesize-research), or to add links to an already-recorded ticket (governance-enrich-ticket). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| mature-resolve-tickettsunami28/MindNovaResolve a confirmed defect surfaced in the mature phase by running a scoped pass of the development cycle. Use when a triaged work item is a reproducible bug ready to fix: phrasings like "fix MN-42", "this defect is confirmed, go fix it", "resolve the bug from triage", "take this confirmed defect through the dev cycle", or when mature-analyze-ticket has handed off a confirmed reproduction. This is a thin entry point that frames the defect and delegates. Do NOT use to triage or confirm an issue first (that is mature-analyze-ticket), to build a new feature or make an ad-hoc code fix with no triaged ticket (use create-code-generation directly), or for a pure structural cleanup with no behaviour change (that is create-refactoring). | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| run-sdlctsunami28/MindNovaNavigate the AI-SDLC workflow for a given work item or artifact: report where it is in the lifecycle and what to do next. Use when the user asks "where are we on MN-42", "what is the next step for this story", "run the sdlc on <key or path>", "what is missing before this can ship", "which phase is this in", or hands over an artifact (a work item key, a spec, a doc, an ADR) and asks how to proceed. It is READ-ONLY for navigation: it resolves the anchor, traverses the artifact graph, and reports the current phase plus the next /<phase>-<step> and the persona who owns it. It does NOT create, edit, link, or transition anything, and it never writes directly; on explicit request it can dispatch the next step by handing off to the owning phase-step skill (which writes behind its own confirmation gates), per docs/ai-sdlc/orchestration.md. Do NOT use to author artifacts or to write work items. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| new-postnewbee1939/h6o記事のタイトルや書きたい内容から slug を決め、scripts/new-post.sh で posts/ に雛形を作る。 | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| benchmarkalexandervashurin/semaphorePerformance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| browsealexandervashurin/semaphoreFast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| canaryalexandervashurin/semaphorePost-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| carefulalexandervashurin/semaphoreSafety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| codexalexandervashurin/semaphoreOpenAI Codex CLI wrapper — three modes. Code review: independent diff review via codex review with pass/fail gate. Challenge: adversarial mode that tries to break your code. Consult: ask codex anything with session continuity for follow-ups. The "200 IQ autistic developer" second opinion. Use when asked to "codex review", "codex challenge", "ask codex", "second opinion", or "consult codex". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| design-consultationalexandervashurin/semaphoreDesign consultation: understands your product, researches the landscape, proposes a complete design system (aesthetic, typography, color, layout, spacing, motion), and generates font+color preview pages. Creates DESIGN.md as your project's design source of truth. For existing sites, use /plan-design-review to infer the system instead. Use when asked to "design system", "brand guidelines", or "create DESIGN.md". Proactively suggest when starting a new project's UI with no existing design system or DESIGN.md. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| design-reviewalexandervashurin/semaphoreDesigner's eye QA: finds visual inconsistency, spacing issues, hierarchy problems, AI slop patterns, and slow interactions — then fixes them. Iteratively fixes issues in source code, committing each fix atomically and re-verifying with before/after screenshots. For plan-mode design review (before implementation), use /plan-design-review. Use when asked to "audit the design", "visual QA", "check if it looks good", or "design polish". Proactively suggest when the user mentions visual inconsistencies or wants to polish the look of a live site. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| document-releasealexandervashurin/semaphorePost-ship documentation update. Reads all project docs, cross-references the diff, updates README/ARCHITECTURE/CONTRIBUTING/CLAUDE.md to match what shipped, polishes CHANGELOG voice, cleans up TODOS, and optionally bumps VERSION. Use when asked to "update the docs", "sync documentation", or "post-ship docs". Proactively suggest after a PR is merged or code is shipped. | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| freezealexandervashurin/semaphoreRestrict file edits to a specific directory for the session. Blocks Edit and Write outside the allowed path. Use when debugging to prevent accidentally "fixing" unrelated code, or when you want to scope changes to one module. Use when asked to "freeze", "restrict edits", "only edit this folder", or "lock down edits". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| gstackalexandervashurin/semaphoreFast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. gstack also includes development workflow skills. When you notice the user is at these stages, suggest the appropriate skill: - Brainstorming a new idea → suggest /office-hours - Reviewing a plan (strategy) → suggest /plan-ceo-review - Reviewing a plan (architecture) → suggest /plan-eng-review - Reviewing a plan (design) → suggest /plan-design-review - Creating a design system → suggest /design-consultation - Debugging errors → suggest /investigate - Testing the app → suggest /qa - Code review before merge → suggest /review - Visual design audit → suggest /design-review - Ready to deploy / create PR → suggest /ship - Post-ship doc updates → suggest /document-release - Weekly retrospective → suggest /retro - Wanting a second opinion or adversarial code review → suggest /codex - Working with production or live systems → suggest /careful - Want to scope edits to one module/directory → suggest /freeze - Maximum safety mode (destructive warnings + edit restrictions) → suggest /guard - Removing edit restrictions → suggest /unfreeze - Upgrading gstack to latest version → suggest /gstack-upgrade If the user pushes back on skill suggestions ("stop suggesting things", "I don't need suggestions", "too aggressive"): 1. Stop suggesting for the rest of this session 2. Run: gstack-config set proactive false 3. Say: "Got it — I'll stop suggesting skills. Just tell me to be proactive again if you change your mind." If the user says "be proactive again" or "turn on suggestions": 1. Run: gstack-config set proactive true 2. Say: "Proactive suggestions are back on." | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| gstack-upgradealexandervashurin/semaphoreUpgrade gstack to the latest version. Detects global vs vendored install, runs the upgrade, and shows what's new. Use when asked to "upgrade gstack", "update gstack", or "get latest version". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| benchmarkalexandervashurin/semaphorePerformance regression detection using the browse daemon. Establishes baselines for page load times, Core Web Vitals, and resource sizes. Compares before/after on every PR. Tracks performance trends over time. Use when: "performance", "benchmark", "page speed", "lighthouse", "web vitals", "bundle size", "load time". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| browsealexandervashurin/semaphoreFast headless browser for QA testing and site dogfooding. Navigate any URL, interact with elements, verify page state, diff before/after actions, take annotated screenshots, check responsive layouts, test forms and uploads, handle dialogs, and assert element states. ~100ms per command. Use when you need to test a feature, verify a deployment, dogfood a user flow, or file a bug with evidence. Use when asked to "open in browser", "test the site", "take a screenshot", or "dogfood this". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| canaryalexandervashurin/semaphorePost-deploy canary monitoring. Watches the live app for console errors, performance regressions, and page failures using the browse daemon. Takes periodic screenshots, compares against pre-deploy baselines, and alerts on anomalies. Use when: "monitor deploy", "canary", "post-deploy check", "watch production", "verify deploy". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |
| carefulalexandervashurin/semaphoreSafety guardrails for destructive commands. Warns before rm -rf, DROP TABLE, force-push, git reset --hard, kubectl delete, and similar destructive operations. User can override each warning. Use when touching prod, debugging live systems, or working in a shared environment. Use when asked to "be careful", "safety mode", "prod mode", or "careful mode". | Stars: 0 | Updated | Claude CodeCodex | Unverified | Install |