claude_skills

Create GitHub Releases with AI-analyzed changelogs for every calendar day with commits on origin/main. Use when creating daily release notes, backfilling releases, or generating AI-categorized changelogs per day. Uses collect → bucket → analyze → synthesize → publish pipeline via Haiku subagents. Idempotent — skips up-to-date days, updates releases where new commits were added. Accepts optional --start-date, --end-date, --branch, and --dry-run arguments.

Enforce anti-AI UI design rules based on the Uncodixfy methodology. Use when generating HTML, CSS, React, Vue, Svelte, or any frontend UI code. Prevents generic AI aesthetic — soft gradients, glassmorphism, hero sections in dashboards, oversized rounded corners, and decorative copy. Applies constraints from Linear/Raycast/Stripe/GitHub design philosophy for functional, honest, human-designed interfaces. Triggers on UI generation, dashboard building, component creation, CSS styling, landing page design, or any task producing visual interface code.

Validate and iterate on the SDLC Layer Separation Architecture implementation across the check categories defined in its Evaluation Checklist — cross-references, doc completeness, knowledge-explorer layer filters, research entry metadata, integration points, and plan consistency. Produces a structured findings report and optionally applies safe fixes. Use when validating a first-pass implementation, before claiming layer work complete, auditing layer docs or schema, or running --dry-run to preview findings without changes.

Test harness for Claude Code skill argument substitution — demonstrates capture-block pre-declaration, XML tag referencing, unintentional variable corruption in code blocks, and correct placement of shell examples in reference files. Use when verifying substitution behavior before applying a pattern to other skills, testing how arguments flow from skill invocations, or understanding the pre-declaration and reference file pattern with greet/farewell/inspect actions.

Verifies claims in backlog items, skill documentation, or plugin content against primary sources using web lookups. Spawns parallel verification agents that must use WebFetch/WebSearch/gh — training data recall is explicitly rejected as evidence. Produces VERIFIED/REFUTED/INCONCLUSIVE verdicts with citations. Use when items are marked UNVERIFIED or when verifying tool API claims, CLI flags, or documented software behavior.

Use when building, extending, or debugging FastMCP v4 (or v3) Python MCP servers. Activates on FastMCP tool/resource/prompt creation, provider and transform implementation (CodeMode, Tool Search), auth setup (MultiAuth, PropelAuth, KeycloakProvider), client SDK usage, FastMCPApp and Generative UI server building, fastmcp-slim client-only installs, nginx reverse proxy deployment, Prefab Apps, OTEL observability, testing, and v3→v4 migration. Grounded in official FastMCP v4 docs plus locally-verified v3 gotchas — zero speculation.

Write and evaluate effective Python tests using pytest. Use when writing tests, reviewing test code, debugging test failures, or improving test coverage. Covers test design, fixtures, parameterization, mocking, and async testing.

Wraps investigation requests with evidence-chain discipline. Use when asked to find out why something happens, research a root cause, debug an issue, or investigate unexpected behavior. Transforms vague investigation requests into reproducible-proof investigations with a 5-step protocol — disambiguate, reproduce, read source, build evidence chain, present findings. Invoke with /find-cause followed by a description of what to investigate.

Use when designing or validating GitLab CI/CD and automatic release lifecycles, inspecting pipeline and job state read-only, composing non-interactive merge-request commands, or setting up protected refs and release credentials. Also covers reusable components and inputs, GitLab Functions, gitlab-ci-local, glab command composition, and GitLab Flavored Markdown. For pipeline execution or retry requests, provide inspection and command drafting while leaving execution to the operator.

Design, build, evaluate, or teach graph-based systems. Use for knowledge graphs, ontology/schema design, entity/relation/event extraction, entity resolution and fusion, GraphRAG or graph memory, and agent/task dependency graphs with concurrency, joins, failure handling, verification, or human gates.

Orchestrator context window discipline enforcement. Prevents the orchestrator from reading source files it will not edit, running diagnostic commands that waste context, and rationalizing delegation bypasses. Use when setting up orchestrator guardrails, reviewing delegation discipline, or diagnosing context window waste in multi-agent workflows. Activates PreToolUse hooks that surface decision points before source file reads and diagnostic command execution.

Same reverse-thinking method as dh:rt-ica (see dh:rt-ica or dh-glossary for the definition), but localizes any MISSING input to the affected task only, as a non-blocking information-completeness pre-pass before task decomposition and plan generation. Use when grooming backlog items, generating plans, decomposing tasks under uncertainty, or working in brownfield and refactor scenarios. Produces completeness summary (APPROVED-FOR-PLANNING, APPROVED-WITH-GAPS, or BLOCKED-FOR-PLANNING), missing input report with dependency mapping, required unblock actions, and planning annotations for downstream tasks. Use dh:rt-ica instead at the S2 implementation gate where missing inputs must halt execution.

Start a local Git rebase when the user explicitly requests replay of a named source ref, or of the current branch, onto a named target, including a rebase-then-push request, or continue or abort an active rebase. Use only when local history replay will start or is active; do not use for merge-based branch updates, repository merge settings, pull-request or merge-request merging, or push-only requests.

Process reviewer feedback for GitHub PRs and GitLab MRs. Use after pushing a commit to recheck reviews, or when asked to check or address comments, questions, approvals, change requests, or bot findings.

Orchestrate research entry lifecycle in ./research/ — create, batch-import, refresh stale entries, and validate structure. Use when asked to add a tool, research a URL, document a library, refresh research, validate entries, or given any tool or library URL. Supports --batch (parallel multi-URL), --rerun (refresh one or all entries), and --validate (structural check with auto-fix of error-severity issues).

Look up prior Claude Code sessions when context is lost or forgotten. Use when asked what was done before, what happened in the last session, or any request to recall past conversation history, prior decisions, experiments, or outcomes. Indexes and searches raw JSONL transcripts from ~/.claude/projects/ via DuckDB. Returns verbatim user messages, summarizes AI actions and sub-agent outcomes, detects tool errors and user frustration signals, and reports tool usage statistics. Summaries cached at ~/.claude/kaizen/session-summaries/.

Builds comprehensive Claude Code skills using parallel research agents — categorization, parallel documentation gathering, anti-hallucination checkpoints, and final validation. Use when building a skill from official docs, when "research for skill" or "create comprehensive skill" is requested, or when extensive multi-source documentation gathering is needed before skill creation.

Research a specific technology, library, system, protocol, or tool to answer a concrete technical question with source-traceable evidence. Use when current implementation details, version behavior, configuration, compatibility, or authoritative technical facts must be verified rather than recalled. Also use when explicitly asked to incorporate verified findings into an existing skill.

Use this skill when reviewing, designing, or improving a workshop, lesson, training session, facilitation plan, talk, or educational explanation. Use it when the user provides a topic, concept, or explanation and wants better framing questions, curiosity hooks, opening prompts, discussion questions, learner reflection prompts, or ways to make participants think before being taught.