Kanevry

Fixture stub — marks this fixture as a plugin-repo audit target (enables c6.3 v2-features-section check).

Use when you have a feature idea but the scope or UX is still ambiguous — runs a lightweight Socratic design dialogue (3-5 AUQ rounds) and writes a spec markdown file. Use BEFORE /plan feature when product intent needs validation; skip to /plan feature when scope is already clear. HARD-GATE prevents any code work until the design is user-approved.

Use when the user asks to improve architecture, find refactoring opportunities, surface deepening opportunities, consolidate tightly-coupled modules, or make a codebase more testable and AI-navigable. Surfaces shallow modules and hypothetical seams using a precise vocabulary (Module / Interface / Implementation / Depth / Seam / Adapter / Leverage / Locality from LANGUAGE.md).

Use this skill when creating today's daily note in the Meta-Vault (03-daily/YYYY-MM-DD.md) with valid vaultFrontmatterSchema-compliant YAML frontmatter. Idempotent: re-running on the same day opens the existing note instead of overwriting. Use when starting a work day, capturing scratch notes, or bootstrapping the inbox flow.

Use this skill when orchestrating documentation generation and updates within a session. Maps session scope to audience-specific docs tasks (User / Dev / Vault), dispatches the docs-writer agent with source-grounded prompts, and reports coverage gaps to session-end. Gated on `docs-orchestrator.enabled: true` in Session Config. Zero overhead when disabled.

Use this skill when executing web tests via the canonical `playwright` npm package (Microsoft, Apache-2.0). Dispatched by `skills/test-runner/` to execute web tests against a target, captures token-frugal AX-tree snapshots + screenshots + console output under `.orchestrator/metrics/test-runs/<run-id>/`, and exits with deterministic JSON output the orchestrator can parse.

Use this skill when performing a full session close-out: verifies all planned work against the agreed plan, creates issues for gaps, runs quality gates, commits cleanly, mirrors to GitHub, and produces a session summary. Triggered by /close command.

Creates a structured wave execution plan with role-based assignment after user alignment. Decomposes agreed tasks into configurable waves (default 5) with optimal agent assignment, dependency ordering, and inter-wave checkpoints. Activated by session-start after Q&A phase completes.

Use when the user wants to define domain terms, build a glossary, harden terminology, create a ubiquitous language, or mentions "domain model" or "DDD". Extracts a DDD-style glossary from the current conversation into UBIQUITOUS_LANGUAGE.md, flags ambiguities and synonyms, and proposes opinionated canonical terms.

Use this skill when dispatching implicit slash-command intent from the user's first message. Inspects the user's first message for implicit slash-command intent and dispatches to the highest-confidence matching entry-point skill via the Skill tool. Only active when `auto-skill-dispatch: true` in Session Config. Silent no-op otherwise.

Use this skill when executing the agreed session plan in waves with role-based execution and parallel subagents. Handles inter-wave quality checks, plan adaptation, and progress tracking. Core orchestration engine for feature and deep sessions. Triggered by /go command.

Use this skill when running an autonomous session-orchestration loop. Chains session-start → session-plan → wave-executor → session-end for N iterations with kill-switches (SPIRAL, FAILED wave, carryover > 50%, max-hours, sub-threshold confidence). Reads Mode-Selector output (Phase B) to decide auto-execute vs. fallback. Writes one autopilot.jsonl record per loop run. Phase C scaffold (issue #277)

Use when detecting drift between CLAUDE.md (or AGENTS.md, the Codex CLI alias) / _meta narrative and live repository state. Seven checks: absolute-path resolution, 01-projects/ count claims, issue-reference freshness (closed refs in forward-looking sections), session-file existence, command-count sync (claimed "N commands" vs actual commands/*.md), session-config-parity (top-level keys diffed agai

Monitor health across configured service endpoints, CI pipelines, and critical issues. Automatically invoked during session-start when ecosystem-health is enabled in Session Config.

Use this skill for structured project planning and PRD generation across three modes: new (project kickoff with repo scaffolding), feature (compact feature PRD), and retro (data-driven retrospective). All modes utilize a researched Q&A engine that dispatches parallel Explore agents, presents options with recommendations, and produces structured documents.

This skill identifies unused, near-zero-use, or stale skills/agents/commands for demotion or retirement. It combines telemetry with static scanning, classifies items into Active/Investigate/Demote/Retire, and generates a Markdown report with a JSON sidecar, never auto-deleting.

Validates Meta-Vault's Markdown frontmatter and wiki-link integrity before closing a session or after edits. It blocks closure if .md files fail schema validation or have dangling wiki-links, supporting hard, warn, or off modes.

Use this skill to extract session patterns into reusable learnings. It offers three modes: analyze (extract from session history), review (edit/manage existing learnings), and list (display active learnings), managing .orchestrator/metrics/learnings.jsonl.

Use this skill for deterministic mode selection at session-start, reading Phase A STATE.md recommendations, learnings, sessions, backlog, and bootstrap signals to return {mode, rationale, confidence, alternatives}. It operates as a pure function with no side effects or STATE.md writes, serving as a Phase B scaffold with the full heuristic in follow-up sub-issues.

Use this skill to reference canonical quality check commands for typecheck, test, and lint. It defines 4 variants (Baseline, Incremental, Full Gate, Per-File) used by session-start, wave-executor, session-end, and session-reviewer, serving as a reference skill not invoked directly.

Use this skill for manual memory consolidation, reviewing, consolidating, and pruning memory files under ~/.claude/projects/*/memory/. Run after major refactors, every 5+ sessions, or if memory quality degrades. Invoke with /memory-cleanup.

Use this skill to initialize a project repo session. It autonomously analyzes git state, VCS issues, SSOT files, branches, environment, and cross-repo status, presenting structured findings and recommendations before creating a wave plan. Triggered by /session [housekeeping|feature|deep].

This skill provides a prepared tmux layout for visualizing session side-channels such as STATE.md, CI-watch, and events.jsonl. It renders a 4-pane default or debug layout for read-only observability, keeping the main chat in the operator's original terminal.

This skill scaffolds the minimum repository structure for session-orchestrator, automatically invoked by the Bootstrap Gate if CLAUDE.md, Session Config, or bootstrap.lock are missing. It also offers manual invocation via /bootstrap and three intensity tiers: fast (demos/spikes), standard (MVPs), and deep (production/team).

Use this skill for systematic quality discovery and issue detection. It runs modular probes adapted to the project's tech stack, presents findings interactively for user triage, and creates VCS issues for confirmed problems, being invokable standalone via /discovery or embedded in session-end.

Use when creating, modifying, or debugging Claude Code hooks like PreToolUse, PostToolUse, and others. This covers plugin and user hook formats, matchers, security, portability, lifecycle, and debugging.

Use when creating, modifying, or optimizing skills, guiding intent capture, structure, and writing patterns to ensure reliable triggering and maintainability. It triggers on phrases like turn this into a skill or my skill isn't triggering.

Use to stress-test a plan against the existing domain model and documented decisions. It conducts a grilling session, interviewing the user, sharpening terminology, updating CONTEXT.md, and sparingly offering ADRs under a 3-criteria gate, reading docs/adr/ and CONTEXT.md if present.

Populates the Meta-Vault with machine-generated notes from session-orchestrator JSONL records. It converts entries from .orchestrator/metrics/sessions.jsonl and .orchestrator/metrics/learnings.jsonl into vault-conformant Markdown, called automatically at session-end Phase 3.7 and after evolve Phase 3.5 — only when vault-integra.

Use this skill when you have a PRD or design spec and require a concise, executable implementation plan that any agent can follow directly. It generates `docs/plans/YYYY-MM-DD-<feature>.md` with detailed tasks, complete code, and exact verification commands, rejecting vague instructions like "TBD" or "TODO".

Use this skill for VCS operations on GitLab or GitHub repositories, such as managing issues, MRs, applying labels, running CLI commands, or resolving project IDs. It serves as the single source of truth for CLI command syntax and label conventions, preventing logic duplication in consuming skills.

Monitors iterative improvement loops for convergence. Three signals — shrinking diff, pass-rate plateau, velocity — drive Stop/Continue/Investigate decisions at each inter-wave checkpoint, answering if progress is being made for /autoresearch loops.

Use for bugs, test failures, build breaks, or unexpected behavior. It runs a 4-phase systematic debugging process, strictly adhering to the Iron Law: no fixes without root cause investigation first, and produces a `.orchestrator/debug/` artifact for the fixer agent.

Injects the canonical vault frontmatter schema snippet into agent prompts before any vault-write task, preventing malformed YAML frontmatter in Obsidian notes.

Use this skill for multi-persona parallel content review by domain experts, buyer personas, compliance reviewers, or custom catalog entries. It dispatches N persona agents in parallel, consolidates verdicts via a configurable mode (voting-quorum, hard-gate-threshold, or coordinator-summary), and writes a timestamped sidecar to .orchestrator/persona-panel/.

This skill is used for creating new MCP (Model Context Protocol) servers, extending existing ones, or debugging tool discoverability and performance. It guides users through research, implementation, testing, and evaluation phases with TypeScript-first guidance aligned with our stack.

Provides a single-pane cross-repository health view for vault-registered GitLab and GitHub projects, aggregating open issues, MRs, critical labels, and stale signals to generate an idempotent `_PORTFOLIO.md` dashboard.

Use this skill when the user wants to audit a repository for baseline compliance, check code quality, security posture, CI/CD setup, testing, documentation, and ecosystem configuration. It runs 9 checklist categories and emits a Markdown report plus a JSON sidecar.

Use this skill when driving native-UI AX-tree snapshots and screenshots via steipete/peekaboo (MIT, macOS-only). Dispatched by skills/test-runner/ to capture native-UI AX-tree snapshots + screenshots on macOS 15+ targets, and exits with deterministic JSON output the orchestrator can parse.

This skill orchestrates agentic end-to-end tests by resolving target and profile, dispatching appropriate drivers (e.g., Playwright for web), and invoking the read-only UX evaluator agent (Opus) against driver artifacts. It then reconciles findings with the issue tracker and generates reports.