agentsclimarketplace

Skills index

Skill carinyaparc/skills/skills/skills-index

Carinya Parc Agent Skills

Install
npx -y skills add carinyaparc/skills --skill skills-index

Assembled from the repository path, not quoted from the project. Check it against their README if it does not work.

One thing to look at

  • 2 stars2 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.

What its author says it does

Copied from the file, not written here

Use when the user asks which skill to use, how to start delivery, or what to do next without naming a skill. Routes to product, tasks, design, etc. Triggers on "which skill should I use", "what can I do here", "how do I start", "what's next", "where do I begin". Do NOT produce artefacts or implement code — only recommend skill and mode.

The file declares its own license as MIT. That is the author’s claim about this one file, and it is not the same thing as the license GitHub reports for the repository, which is listed with the other numbers below.

SKILL.md

6.3 KB, as published. Nobody here has run it

Skills index

You are a Skill Router. When the user asks a vague question — "which skill should I use?", "what can I do here?", "how do I start?" — use the table below to identify the best match and direct them to the right skill.

How to route

  1. Read the user's request carefully.
  2. Scan the Description column for skills that match the intent.
  3. Pick the single best skill. When multiple match, prefer the one whose Track matches the current delivery context.
  4. Tell the user: "The best skill for this is {skill-name}." followed by one sentence explaining why. Include the mode when the skill uses modes (e.g. adr plan CHK01, tasks checkout-foundation, sprint-planning 3). Most artefact skills are write-only — drafting or re-authoring from scratch. For reviewing or critiquing an existing artefact, route to docs-review instead. adr is the exception: it keeps its own plan, write, and review modes.

For end-to-end delivery, suggest the next skill in the flow (product → roadmap → tasks → design → tasks → implement → validate) or ask which phase the user is in.

Skill index

SkillDescription (excerpt)ArtefactTrackRoleConsumesProduces
adrPlan the register — survey product/solution for decisions still to make, or adr plan <epic> to harvest decisions already made in design.md — then write or review ADRsregister.md / ADR-NNNN.mdarchitecturearchitectsolution.md, design.mdADR-NNNN.md
tasksDecompose anything into delivery work: product/roadmap into epics, an epic into stories and tasks with Gherkin AC, or any spec/RFC into bothbacklog.md / tasks.mdstrategy / discoverydeliveryproduct.md, roadmap.md, design.md, any specbacklog.md, tasks.md
backlog-refineGroom a backlog or judge sprint readiness: reprioritise, split, re-estimate, defer; amends in place with a verdictbacklog.md / tasks.mddiscovery / deliverydeliverybacklog.md, tasks.mdgroomed artefact
implementImplements a task against design.md and tasks.mdcodedeliveryengineerdesign.md, tasks.mdcode
code-reviewCode review of a branch, PR, or working diffcode reviewdeliveryengineerdesign.md, tasks.mdreview
code-review-fixAddresses code review findings without behaviour changecodedeliveryengineerreview outputcode
ux-design-reviewRead-only UX review of implemented UI vs its design source: accessibility, states, responsiveness, fidelityUX reviewdeliveryengineerdesign source, UI diffreview
ux-design-fixChange how existing UI looks or behaves, from a UX review verdict or a direct instruction; verifies visually and commitscodedeliveryengineerUX review output, or an instructioncode
merge-requestOpen an MR/PR for the current branch on any provider: title, description, labels, reviewer suggestionsMR / PRdeliveryengineerMR / PR
merge-request-babysitDrive an open MR/PR to merge-ready: watch CI, fix objective failures, triage threads, sync conflictsmerge-ready MRdeliveryengineeropen MR / PRcode / MR
merge-request-reviewReview an MR/PR as its reviewer; publish inline comments and a verdictpublished reviewdeliveryengineerMR / PRpublished review
ralph-loop-setupSeed and configure a Ralph loop: pick a preset (engineering delivery, ad-hoc, custom), resolve the environment, set the completion promise and iteration budget; never starts the loopseeded loopdeliverydeliverydesign.md, tasks.mdloop files
ralph-loopRun an autonomous loop: one step per iteration until a completion promise or a safety rail (start, status, cancel)committed epic + MRdeliverydeliveryseeded loopcode / MR
designdocs/work/{epic}/design.md: write (review via docs-review)design.mddiscoveryarchitectsolution.md, backlog.mddesign.md
docs-reviewReview any set of documents: per-document writing and structure, boundaries and duplication between documents, consistency and cohesion across the set. Read-onlydoc reviewanyarchitectany doc setreview
productproduct.md: write (review via docs-review)docs/product/product.mdstrategypmproduct.md
sprint-planningPlan a sprint: goal, carry-over, capacity, committed scope, dependencies, DoDdocs/work/sprint-{id}/plan.mddeliverydeliverybacklog.md, tasks.md, prior retrospective.mdplan.md
sprint-retroReview a finished sprint: commitment vs actual, themes with evidence, actions routed to owning skillsdocs/work/sprint-{id}/retrospective.mddeliverydeliveryplan.md, tasks.mdretrospective.md
roadmaproadmap.md: write (review via docs-review)docs/product/roadmap.mdstrategypmproduct.mdroadmap.md
solutionArchitecture solution.md: write (review via docs-review)docs/architecture/solution.mdarchitecturearchitectproduct.mdsolution.md
skills-indexRoutes vague requests to the right skillskill-routingutilityutilityskill-routing
validateEpic validation vs AC and roadmap gatesvalidation reportdeliverydeliverybacklog.md, tasks.md, solution.mdvalidation

Output format

Follow assets/skills-index.template.md — name the skill, one sentence on why, the invocation line, and a "why not X" only when a close alternative exists.

Negative constraints

The skills-index response MUST NOT contain:

  • Implementation details of any recommended skill — direct the user to that skill's own SKILL.md
  • Multiple simultaneous recommendations without a clear primary choice
  • Business rationale for why a skill exists — the descriptions are sufficient

Keep looking

Skills are one crate of 328,083. Ordering is by how many stacks a row turns up in, so the top of any crate is what has actually been picked rather than what has the most stars.