All authors
Claude Skills by closedloop-ai
github.com/closedloop-ai46 skills0 installs51 views
- FixVerify and fix BLOCKING/HIGH code review findings from a prior review session, then run project verification.Votes: 0GitHub stars: 122
- Context EngineeringThis skill should be used when designing prompts, system prompts, or context windows for Claude. Triggers include writing prompts for API calls, designing agent instructions, structuring complex inputs, optimizing context for accuracy, using examples effectively, or implementing chain-of-thought reasoning. Provides comprehensive guidance from Anthropic's official prompt engineering documentation.Votes: 0GitHub stars: 122
- HandoffFinish a vibe session in symphony-alpha and hand it to whoever picks it up next, usually design and then engineering. Shows the person a task list, then (through workers) checks the work stays within its scope, makes sure every new or changed component has Storybook stories, runs lint, typecheck, and tests (the whole suite for a full-scope session), runs the code reviews (an adversarial review, or two workflow-code-review passes for full scope) and fixes what they confirm, asks who should pic...Votes: 0GitHub stars: 122
- Vibe Seed RefreshKeep symphony-alpha's vibe seed (the throwaway, fully seeded data behind `just vibe-up` and the vibe skill's seeded Vercel environments) in step with main. Checks fresh main for seed drift (models marked todo, models with no coverage file, a failing seed, a red Vibe Seed Walk run on main); when drift exists it creates a ClosedLoop ticket and marks it IN_PROGRESS, has workers fix the seed in a fresh worktree and open a PR, monitors it with gh-monitor-pr until green, enables auto-merge into the...Votes: 0GitHub stars: 122
- VibeStart or resume a vibe-coding session in symphony-alpha for a non-engineer (built for Andy, the CEO) working in the Codex Desktop in-app browser. Sets up the machine, creates or resumes an isolated worktree off fresh main, asks what part of the app to work on (a ClosedLoop ticket or a plain description) and whether the environment should be seeded with sample data or blank, creates the session's live ClosedLoop ticket, and stands up the session's own Vercel environment (web app, API, Storyboo...Votes: 0GitHub stars: 122
- Build Status CacheSkip Phase 7 rebuild when no code changed since Phase 5 build passed. Compares git diff hash against stored hash from last successful build validation. Triggers on: entering Phase 7, checking build status, before final build validation. Returns BUILD_CACHE_HIT to skip or BUILD_CACHE_MISS to re-run build-validator.Votes: 0GitHub stars: 121
- Closedloop EnvProvides ClosedLoop environment paths (CLOSEDLOOP_WORKDIR, CLAUDE_PLUGIN_ROOT) to agents. This skill should be used by any agent that needs to access ClosedLoop run directories, plugin schemas, or other path-dependent resources.Votes: 0GitHub stars: 121
- Codex ReviewRun Codex to review a plan file and return structured feedback with a verdict. Triggers on: debate loop Codex review rounds. Returns VERDICT:APPROVED or VERDICT:NEEDS_CHANGES plus CODEX_SESSION token.Votes: 0GitHub stars: 121
- Critic CacheCheck if critic reviews are still valid before re-running Phase 2.5 critics. Compares plan.json + critic-gates.json content hash against stored hash from last critic run. Triggers on: entering Phase 2.5, checking critic cache, before launching critics. Returns CRITIC_CACHE_HIT to skip critics or CRITIC_CACHE_MISS to re-run them.Votes: 0GitHub stars: 121
- Cross Repo CacheCheck if cross-repo coordinator results can be reused, avoiding redundant Sonnet agent launches. Compares peer repo git hashes against stored hashes from last coordinator run. Triggers on: entering Phase 1.4.1, checking cross-repo cache, before discovering peers. Returns CROSS_REPO_CACHE_HIT with cached status or CROSS_REPO_CACHE_MISS to re-run coordinator.Votes: 0GitHub stars: 121
- Decision TableUse when the user wants a code-grounded decision table for current behavior, wants to compare current behavior against a plan or work item, or needs a control-flow artifact for recovery, retry, finalization, validation, state-machine, or review-heavy edge cases.Votes: 0GitHub stars: 121
- Extract Plan MdSync plan.md with plan.json content. MUST be used after ANY edit to plan.json to keep plan.md in sync. Triggers: - After editing plan.json with Edit tool (REQUIRED - always sync after edits) - User asks to "sync plan.md", "update plan.md", "extract the md from a plan" - Converting plan.json to markdown or viewing plan as standalone markdown IMPORTANT: Whenever plan.json is modified, plan.md must be updated to match.Votes: 0GitHub stars: 121
- Find Plugin FileThis skill should be used when needing to locate files within the Claude Code plugins cache directory (~/.claude/plugins/cache). Triggers include finding tool scripts, skill files, or any plugin resource when the hardcoded path is unknown or varies by plugin version. Use when slash commands or orchestrators need to dynamically resolve plugin file paths.Votes: 0GitHub stars: 121
- Iterative RetrievalProtocol for iteratively refining sub-agent queries through follow-up questions to ensure sufficient contextVotes: 0GitHub stars: 121
- Plan Editing ConventionsConventions for editing plan.json implementation plans including task format, structured arrays, and plan structure rules. Use when creating or modifying plan.json files.Votes: 0GitHub stars: 121
- Plan StructureUsed when creating or updating implementation plans.Votes: 0GitHub stars: 121
- Plan ValidateDeterministic plan.json validation via Python script, replacing most plan-validator agent calls. Performs JSON parsing, schema validation, task checkbox regex, required section checks, sync validation, and data extraction. Only semantic consistency checks (storage/query alignment) require the LLM agent. Triggers on: plan validation, checking plan format, extracting plan data. Returns PLAN_VALID with extracted data or PLAN_FORMAT_ISSUES with issues list.Votes: 0GitHub stars: 121
- Prd CreatorThis skill helps PMs draft lightweight PRDs. It should be used when a PM wants to define a new feature, brainstorm requirements, or prep for sprint planning. Triggers include "I have a feature idea", "help me write a PRD", "let's break this into stories", or "what do I need for sprint planning". Optimized for speed — generates minimal viable documentation through conversation, not heavy templates.Votes: 0GitHub stars: 121
- Artifact Type Tailored ContextCompresses artifacts for judge evaluation. Reads a single raw artifact, applies tiered summarization within a token budget, and returns compacted content with metadata. Isolation via forked context prevents pollution of agent contextVotes: 0GitHub stars: 121
- Eval CacheCheck for a cached plan-evaluation.json result before launching the plan-evaluator agent. This skill should be used in Phase 1.3 (Simple Mode Evaluation) of the orchestrator prompt. Triggers on: entering Phase 1.3, checking simple mode, evaluating plan complexity. Returns EVAL_CACHE_HIT with cached values or EVAL_CACHE_MISS signaling re-evaluation is needed.Votes: 0GitHub stars: 121
- Run JudgesOrchestrate parallel judge agent execution, aggregate CaseScore results, write plan-judges.json, code-judges.json, prd-judges.json, or feature-judges.json, and validate output. Supports evaluating implementation plans (16 judges, 4 batches), code artifacts (11 judges, 3 batches), PRD artifacts (5 judges, 2 batches), or Feature artifacts (3 judges, 1 batch) via --artifact-type parameter.Votes: 0GitHub stars: 121
- Claude Code ExpertThis skill should be used when working with Claude Code infrastructure including agents, skills, slash commands, hooks, plugins, settings.json, or CLAUDE.md files. Triggers on YAML frontmatter, .claude/ directory files, Task tool configuration, or hook debugging. Do NOT use for creating NEW skills from scratch - use claude-creator instead.Votes: 0GitHub stars: 121
- Claude CreatorGuide for creating NEW skills from scratch. This skill should be used when users want to create a new skill or scaffold a skill directory. Triggers on "create a skill", "new skill", or "scaffold skill". Do NOT use for updating existing skills - use claude-code-expert instead.Votes: 0GitHub stars: 121
- Mermaid VisualizerThis skill should be used when a user asks to explain a complex idea, concept, or system architecture, or when a diagram would be helpful to visualize control flows, system architectures, data flows, state machines, sequence diagrams, or entity relationships.Votes: 0GitHub stars: 121
- Upload ArtifactUpload a file as a ClosedLoop document (PRD, implementation plan, feature, or template). Reads file content and uploads via MCP without consuming conversation context. Also supports creating new versions of existing documents. Triggers on: "upload artifact", "upload PRD", "upload implementation plan", "upload feature", "create artifact from file", "save as artifact", "push to closedloop", "new artifact version", "test artifact upload", "verify artifact content", "upload to project".Votes: 0GitHub stars: 121
- Learning QualityStructured format for capturing high-quality learnings during ClosedLoop runsVotes: 0GitHub stars: 121
- Toon FormatThis skill should be used when writing or parsing TOON (Token-Oriented Object Notation) files. Triggers on .toon file operations, org-patterns.toon generation, or when converting between JSON and TOON formats. Provides syntax rules, quoting conventions, and examples for LLM-optimized data serialization.Votes: 0GitHub stars: 121
- Present LocalRender the operator-facing local-mode code review results at stage_29_present. Covers BLOCKING/HIGH/MEDIUM section templates, Justified Findings (PLN-721), Dismissed Findings (PLN-722), Verifier Stats footer (PLN-773), operator-flag descriptions, override precedence rule for stage_22b, Validation Summary, and final Summary. Invoke when MODE=local AND stage_29_present is reached. Do NOT use for GitHub mode — see prompts/github-review.md. Do NOT use for Gate A hygiene-only early-exit — that pat...Votes: 0GitHub stars: 121
- Singleton DispatchPLN-725 single-agent dispatch for stage_11_extract_signals and stage_15_coverage_critic. After each prepare stage writes its manifest, this skill reads the status field (cache_hit / skipped / needs_agent) and, only on needs_agent, spawns one synchronous singleton Task that writes the by-convention pln725_*.json output the sibling consolidate stage consumes. Invoke from walker-contract step 6 immediately after stage_11_extract_signals or stage_15_coverage_critic finishes. Do NOT use for the re...Votes: 0GitHub stars: 121
- Spawn ReviewersSpawn and collect the reviewer fleet at stage_20_spawn_reviewers. Consumes spawn.json.spec (the authoritative spawn spec from derive-spawn-spec / derive-static-spec), resolves CODE_INTEL_ALLOWED and CODE_INTEL_REQUIRE_ROOT_ARG, builds per-agent prompts from the per-agent template + role suffixes (Bug Hunter A/B, Unified Auditor, Domain Critics, Impact Analyzer), handles the standard, fast-path, all-cached-BHA, and gated-by-verify cases, and runs the spawn/collection contract and agent-failure...Votes: 0GitHub stars: 121
- Verify FindingsDispatch and collect the finding-verifier fleet at stage_23_verify_findings (PLN-722). Reads verify_manifest.json (written by stage_22b_verify_prepare), spawns one falsify-oriented verifier Task per to_verify[] entry with mode-specific Task scheduling (GitHub mode dispatches verifiers synchronously; local mode uses parallel background + blocking TaskOutput), skips cache_hits[], and collects outputs without retry — missing outputs degrade to pending_verification[] (and, in GitHub mode, a missi...Votes: 0GitHub stars: 121
- Design InventoryUse to run the Claude Design to ClosedLoop pipeline against the current web-ui. Stage A inventories a design export zip into schema-validated findings (typed design units - screens, regions like nav bars, standalone components like a chat dialog; UX and behavioral changes; Storybook component reuse mapping; token drift vs the live design system), then creates a platform "Design Review" Feature document the team reviews by editing. Stage B is that in-document human review (delete a section to ...Votes: 0GitHub stars: 121
- Orchestrator SequencesCanonical reusable orchestration procedures for the ClosedLoop planning/implementation orchestrators — PLAN_VALIDATION_SEQUENCE and AWAITING_USER_SEQUENCE. Single source of truth shared by prompts/prompt.md (full loop), prompts/plan-prompt.md (/code:create-plan) and prompts/execute-prompt.md (/code:execute-implementation), which each load standalone and cannot reference one another at runtime. Triggers: - An orchestrator phase needs full plan validation (structural + semantic) — run PLAN_VAL...Votes: 0GitHub stars: 121
- Guided Manual QaDerive and run an interactive, evidence-recorded manual QA session for a code change, ticket, branch, or pull request. Use when a human should validate live behavior checkpoint by checkpoint after repository-aware setup; do not use as a substitute for automated tests or a read-only code review.Votes: 0GitHub stars: 121
- Cl AnalyzeAnalyze one ClosedLoop feature ticket from a URL or FEA slug before execution. Use when asked to assess ticket complexity, feasibility, readiness, applicable requirements PRDs and missing PRD links, UI design guidance, human UI plan approval needs, blockers, legacy split lineage, merge-batch compatibility, nonsensical or obsolete scope, product versus engineering routing, or whether a ticket can safely be worked before invoking $cl-execute. Keep engineering and operational concerns private; r...Votes: 0GitHub stars: 121
- Cl ExecuteDraft and upload ClosedLoop implementation plans with Mermaid scope flowcharts, then execute one ClosedLoop feature ticket or a parent-approved coherent multi-ticket feature end to end on Codex Desktop or as a leased Codex CLI ticket worker after all readiness, legacy split-lineage, complexity, risk, requirements, batch, and UI guidance gates. Plan, implement, run the required two-pass coordinated review sequence, validate, open and remediate the feature's single PR, maintain the author-owned...Votes: 0GitHub stars: 121
- Cl Find Related TicketsInspect the relevant code first to map the implementation blast area, then find ClosedLoop issue tickets related to a product area, behavior, requirement, incident, ticket, or pull request and give a brief evidence-based reason for each match. Use when auditing scope, finding potentially conflicting or missing work across projects and assignees, checking whether a freeze covers every relevant ticket, comparing discoveries with an approved ticket set, or looking for direct changes, dependencie...Votes: 0GitHub stars: 121
- Cl PolicyShared ClosedLoop access and routing policy for local ClosedLoop automation skills. Use when cl-analyze, cl-split, cl-sweep, or cl-execute needs to discover ClosedLoop tools, select a safe MCP/CLI/API access fallback, resolve product contacts or engineering attention contacts, apply comment tagging and first-person communication rules, load local overrides, or interpret legacy personal-name memory fields.Votes: 0GitHub stars: 121
- Cl SplitSplit one top-level high-complexity ClosedLoop feature ticket into smaller executable child tickets when safe. Use when $cl-analyze or $cl-sweep determines a top-level ticket is HIGH complexity but potentially splittable, or when asked to decompose a FEA-* ticket before execution. Keep engineering/split automation details private; recommend a company-visible comment only for a genuine Product decision under cl-policy or when the user explicitly requests the exact comment. Enforce one split le...Votes: 0GitHub stars: 121
- Cl SweepReport or coordinate ClosedLoop work assigned to the user in one project. Use read-only report mode for a complete project-wide inventory grouped into product-feature context with dependency and reassignment guidance. For execution, recover active work first, then run each selected complete page or capability as one owner, branch, plan, PR, and manual-QA unit while preserving every ticket's independent readiness and acceptance gates. Supports Codex Desktop and a fail-closed CLI root with dura...Votes: 0GitHub stars: 121
- Cl Work ReportProduce a private, read-only HTML report of all ClosedLoop work assigned to the authenticated user in one project, grouped into evidence-backed page or capability feature units with verified dependencies and minimal reassignment recommendations. Use for project work inventories, feature-unit reports, blocker ownership, or reassignment advice; do not use it to execute, reassign, or update tickets.Votes: 0GitHub stars: 121
- Closedloop IntelClosedLoop ticket + codebase intelligence over a shared remote instance. Use PROACTIVELY for questions about ticket scope overlap or duplicate work ("do these tickets overlap", "is someone already doing this", "is this a duplicate"), blast radius ("if I change this file or symbol, what breaks", "which tickets touch this code", "what depends on this module"), ticket lookup by keyword or slug, ticket lineage (which plan produced which issue, branches and PRs for a ticket), and aggregate rollups...Votes: 0GitHub stars: 121
- Gh Monitor PrStart a detached GitHub pull-request monitor that wakes the exact launching Codex Desktop or CLI root through the managed Codex App Server when review, CI, conflict, merge-queue, closure, readiness, or merge events need attention. Use when the user asks Codex to watch, monitor, babysit, or wait on a PR or merge queue without keeping the current turn alive.Votes: 0GitHub stars: 121
- Measurement DisciplineUse when optimizing, benchmarking, profiling, or running a performance experiment; when evaluating whether a change actually helped; or when recording or checking past optimization attempts. Enforces one-variable experiments, noise floors measured from repeated runs, a required mechanism behind any claimed win, and writing refutations down so failed attempts are not re-litigated.Votes: 0GitHub stars: 121
- Mermaid VisualizerThis skill should be used when a user asks to explain a complex idea, concept, or system architecture, or when a diagram would be helpful to visualize control flows, system architectures, data flows, state machines, sequence diagrams, or entity relationships.Votes: 0GitHub stars: 121
- Workflow Code ReviewRun a worker-backed code review using the workflow prompt pack's strongest review lenses: approach correctness, architecture ownership, correctness, guardrails, validation, compatibility, and security. Use when asked to review a PR, branch, diff, or uncommitted changes with workflow-level rigor.Votes: 0GitHub stars: 121