Skip to content

Explore skills

Search every indexed skill by name, description, repository or instructions, then narrow the results.

Showing 60121–60150 of 61000 skills

ts-pnpm-workflowGravionLabs/elysionAdopt pnpm as the package manager or migrate from npm (install, lockfile, scripts). Use when starting a Node project or migrating an npm project to pnpm.Stars: 0Updated Claude CodeCodexUnverifiedInstall
ts-testGravionLabs/elysionTypeScript/Node.js test rules using Vitest (runner config, file naming, mocking, coverage). Use when writing or running tests in a TypeScript or Node.js project.Stars: 0Updated Claude CodeCodexUnverifiedInstall
create-code-generationtsunami28/MindNovaOrchestrate a feature or fix from story to PR through the team's AI-SDLC workflow, with human checkpoints: story -> plan -> branch -> TDD (>=80% coverage, story-tagged tests) -> update both doc layers -> record decisions as ADRs -> enrich the work item -> review -> PR. Use when the user says "take this story through the process", "run the dev cycle", "do the full workflow on MN-42", or "build this end to end properly". It delegates to focused skills rather than doing each step itself. Do NOT use for a quick one-off edit, a question, or a standalone git or branch request (creating or naming a branch on its own) - use the individual skills directly for those.Stars: 0Updated Claude CodeCodexUnverifiedInstall
create-refactoringtsunami28/MindNovaImprove the internal structure of existing code without changing its observable behaviour. Use when the user says "refactor this", "clean this up", "simplify this", "extract a method/class", "rename for clarity", "reduce this duplication", or "tidy this without changing behaviour". The defining constraint is behaviour preservation: the tests pass before and after, and the public contract is unchanged. Do NOT use to add or change behaviour, fix a bug, or build a feature (that is create-code-generation), and do NOT use to delete dead code as the primary goal.Stars: 0Updated Claude CodeCodexUnverifiedInstall
create-run-gatestsunami28/MindNovaRun all the CI code-analysis gates locally against a change, before opening a PR, so failures are caught in seconds instead of after a full pipeline cycle. Use when the user says "run the gates", "check before I push", "will CI pass", "run the CI checks locally", "did I break a gate", or "pre-PR check", or as the verification step at the end of a change. Do NOT use to evaluate a skill's quality (that is governance-validate-skills) or to validate only the artifact graph and docs wiki (that is governance-check-graph); this runs the whole gate set the pipeline runs.Stars: 0Updated Claude CodeCodexUnverifiedInstall
create-sprint-planningtsunami28/MindNovaAssemble refined, sized stories into an iteration and order them by dependency and value so the build phase starts with a clear, unblocked queue. Use when the user says "plan the sprint", "what should we pick up next", "fill the iteration", "sequence these stories", "order the backlog for the next sprint", or "assign these to the sprint". This is a light coordination step, not a document-producing one. Do NOT use to create or refine a story (that is elaboration-upsert-user-story), to write acceptance criteria (that is elaboration-upsert-user-story-acceptance-criteria), to take a single story through build (that is create-code-generation), or to report the next step on a single work item (that is run-sdlc).Stars: 0Updated Claude CodeCodexUnverifiedInstall
create-upsert-documentationtsunami28/MindNovaMaintain BOTH documentation layers as one linked wiki after a change: technical docs in docs/ and functional docs in docs-functional/. Use after implementing or changing a feature, when the user says "update the docs", "sync the documentation", "the docs are out of date", "document how this works", or as the documentation step of a development cycle. Also use when a good answer to a real question deserves to become a page. Reads the layer index first, routes each change to the right layer, cross-links related pages, and flags stale sections. Do NOT use for ADRs (governance-author-adr), the constitution (governance-constitution), or API spec / OpenAPI generation.Stars: 0Updated Claude CodeCodexUnverifiedInstall
create-verify-test-coveragetsunami28/MindNovaVerify a change is adequately tested before it ships: run the tests, measure line coverage on the changed projects, and confirm every acceptance criterion has a covering test. Use when the user says "is this tested enough", "check the coverage for MN-42", "are all the ACs covered", "verify the tests before the PR", "run the QE checks", or "is this story gate-ready". Do NOT use to WRITE the implementation or the tests (that is create-code-generation), to derive or number the criteria (that is elaboration-upsert-user-story-acceptance-criteria), or to review code style (that is the review step).Stars: 0Updated Claude CodeCodexUnverifiedInstall
discovery-map-journeytsunami28/MindNovaMap the customer journey and opportunity landscape for a discovery theme as a diagram, exposing pains and opportunities before any solutioning. Use when the work needs a visual of the experience: phrasings like "map the customer journey", "draw a journey map", "where do users feel pain in this flow", "lay out the opportunity landscape", "visualise the as-is experience", "what are the stages and pain points", or when a Discovery/Spike needs its journey made navigable. Do NOT use to run or synthesise the research itself (that is discovery-synthesize-research), to frame the riskiest assumptions (that is discovery-upsert-hypothesis-canvas), to turn opportunities into stories or create tickets (that is elaboration-upsert-user-story), or to add links to an existing issue (that is governance-enrich-ticket).Stars: 0Updated Claude CodeCodexUnverifiedInstall
discovery-synthesize-researchtsunami28/MindNovaTurn raw research into a synthesis anchored on a local Discovery/Spike work item under docs/discovery/. Use when research has been gathered and needs to become navigable findings: phrasings like "synthesise this research", "write up the interview findings", "summarise the research study", "what did the user research conclude", "turn this research into something the team can act on", "anchor this study to a Spike", or when discovery work is done and should feed elaboration. This is the entry point to the discovery phase. Do NOT use to run or collect the research itself (that happens upstream), to create an ordinary feature story (that is elaboration-upsert-user-story), to author an ADR (governance-author-adr), or to add links to an already-synthesised item (governance-enrich-ticket).Stars: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall
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: 0Updated Claude CodeCodexUnverifiedInstall