Showing 48061–48090 of 77200 skills
Independently judge whether a Spec's design is ready to be built on — requirement coverage, boundary, buildability, self-containment, and architectural fit.
Huruikagi/pc-build-planner
Use only when every Task for a named Spec is complete and the user explicitly asks for lifecycle validation against the active Requirement IDs that records completion on GO. For a consequence-free claim check, use sb-verify-completion.
Huruikagi/pc-build-planner
Consequence-free check of an explicit completion or success claim against fresh evidence. Changes nothing; do not use to advance a named Spec whose implementation may be accepted.
Huruikagi/pc-build-planner
Configure or explicitly update SpecBind for a project and complete the resulting aftercare. Use for an explicit SpecBind binary or project-asset update request, initial post-install review, or later changes to Agents, role models, artifact language, project instructions, templates, shared Rules, operational adapters, Steering, or existing artifacts affected by configuration changes.
Huruikagi/pc-build-planner
Judge whether the milestone's changes leave every persistent seam in the project coherent, and accept the one contract review that Tasks authoring waits on.
Huruikagi/pc-build-planner
Use directly when the user asks why a Task failed or cannot be implemented. Establish the root cause, categorize it, and return a next action. Read-only; never starts implementation or applies the fix.
Huruikagi/pc-build-planner
Turn a change request or Source Collection into confirmed Spec and milestone boundaries.
Huruikagi/pc-build-planner
Drive the active milestone through every safe reachable planning, implementation, and validation action. Park branch-local attention and continue elsewhere; stop before release execution.
Huruikagi/pc-build-planner
Compare what a change needs against what the repository already provides, and record the findings worth keeping. Informs the decision; does not make it.
Huruikagi/pc-build-planner
Implement or resume one roadmap item — executing a Spec's approved task plan through returned review or diagnosis with dispatched implementers and reviewers, or performing and completing a Direct change. Do not use for a diagnosis-only request asking why work failed or cannot be implemented.
Huruikagi/pc-build-planner
Plan active Spec work through Requirements, Design, Contract Review, and Tasks, run one explicitly requested planning phase for one named Spec, or prepare explicitly scoped project shared Contracts. Ordinary Spec planning uses one named Spec or explicit all-Spec scope.
Huruikagi/pc-build-planner
Close the active milestone — bind the version, run the project's release procedure, judge whether it worked, and finalize the whole milestone once it did.
Huruikagi/pc-build-planner
Judge whether one implemented task is done correctly, from the actual diff and the approved requirements, design, and plan.
Huruikagi/pc-build-planner
Report where a Spec or active milestone is in its lifecycle and what can happen next. Read-only; do not use to judge whether completed implementation is actually done.
Huruikagi/pc-build-planner
Maintain durable project guidance — bootstrap it, synchronize it after code changes, or document a long-lived project convention such as testing, API, security, or deployment.
Huruikagi/pc-build-planner
Independently judge whether a Spec's design is ready to be built on — requirement coverage, boundary, buildability, self-containment, and architectural fit.
Huruikagi/pc-build-planner
Use only when every Task for a named Spec is complete and the user explicitly asks for lifecycle validation against the active Requirement IDs that records completion on GO. For a consequence-free claim check, use sb-verify-completion.
Huruikagi/pc-build-planner
Consequence-free check of an explicit completion or success claim against fresh evidence. Changes nothing; do not use to advance a named Spec whose implementation may be accepted.
Huruikagi/pc-build-planner
Reference for the Discovery phase: requirements discovery and scoping.
ilandahan/AID
Website Operations OS for AI Agents. Use this skill whenever an agent must understand, modify, deploy, verify, troubleshoot, secure, back up, or operate a website — especially a production website. Enforces risk assessment, backup-before-risk, stop conditions, semantic production verification, fix-one-scan-class, and a self-improving local experience loop. Triggers: deploy / release, website down, 500 errors, bad deployment, database or data changes, DNS or domain changes, SSL issues, SEO checks, performance problems, backup and recovery, security review, incident response, rollback, "check my website", "fix my site".
DitoSun/sitepilot
微信读书助手 — 搜索书籍、管理书架、查看笔记划线、浏览书评、阅读统计、发现推荐好书
Tencent/WeChatReading
Patterns for continuous autonomous agent loops with quality gates, evals, and recovery controls. Use when running an agent loop that must self-check, gate on evals, and recover from failures.
supreme12343/Stai-Project
Drafts or rewrites a work message without changing its ask or stance; use only when the user says "compose", "run compose on" or "polish this message", or asks Claude to draft a message Claude will post or send for them (Slack, email, Jira comment).
by-carlos/daikenja
Reviews a document against a predetermined checklist: clarity, undefined terms, unenforced rules, undated decisions, missing owners, contradictions, and obvious stale content. Use when the user says "review this doc", "review this page", "check this before I publish", or pastes a document and asks for a check before sharing it. Read-only -- it reports findings, it never edits or rewrites the document.
by-carlos/daikenja
Checks a thread or a document against the project ledger and general knowledge and hands back a verdict: what is being claimed or asked, which parts a recorded decision settles, which parts are plain fact, and what is presented as settled without being established. Use when the user says "is this right?", "check this against the ledger", "give me a judgement on this thread", or asks for a quick "AI review summary" of a page or pull request to share with the team. Read-only -- it never drafts a reply, never edits the document and never writes the ledger.
by-carlos/daikenja
Derives your writing-style.md from writing samples you supply, backing up whatever the file held first. It records style rules only, never facts about people or projects.
by-carlos/daikenja
Turns a meeting transcript into proposed ledger entries: decisions made, action items with owners and dates, and questions left unresolved. Use when the user pastes a transcript or asks what came out of a call. It classifies only and writes nothing itself.
by-carlos/daikenja
Challenges a draft before it goes out and hands back a revised version plus the facts only you can supply -- the six substance checks, then a set of reviewer personas whose wording problems it fixes. Never sends anything.
by-carlos/daikenja
Reports what changed in a project's Daikenja ledger since the user last checked, read from git history of each repository's DECISIONS.md and the home repository's open.md, then advances each repository's checkpoint on approval. The only skill that writes last_checkpoint in daikenja.yaml; it never touches ledger content. Accepts an optional project key -- `/daikenja:project-catchup <key>` reads that project from anywhere.
by-carlos/daikenja
Looks up what is decided about a specific topic in a project's Daikenja ledger -- the decisions in force in every repository's DECISIONS.md -- with each entry's history from git and its linked issue or ADR, plus the open items that bear on it. Read-only; writes nothing. Accepts an optional project key -- `/daikenja:project-decisions <key>` reads that project from anywhere.
by-carlos/daikenja