Loading...
Loading...
Found 6,664 Skills
Convene a structured LLM Council — five thinking-lens advisors (Red Team, First Principles, Expansionist, Outsider, Executor) plus anonymised peer review, forced debate on consensus, dual-chairman synthesis with dissent preservation, and optional Codex-powered Decision Science pass — to pressure-test high-stakes decisions. Adaptive modes (Quick/Standard/Deep) keep cost bounded; a persistent journal enables learning across runs. Mandatory triggers: /claude-council, "convene the council", "run this by the council", "I need the council", "council this", "pressure-test this", "stress-test this", "war room this", "debate this". Strong triggers: "I'm torn between X and Y", "this is a big decision", "help me think this through from multiple angles", "I need outside perspectives", "should I X or Y" (with real stakes — if binary with obvious answer, triage rejects per Step 1 rule 4). Do NOT invoke for factual questions, coding help, debugging, quick yes/no decisions, emotional support, or questions with one right answer — answer those directly. Optional suffixes: "with codex" enables Decision Science pass; "deep" forces Deep mode; "quick" forces Quick mode. Secondary invocation: /claude-council outcome <sha1> <note> records decision outcome. /claude-council meta runs journal meta-analysis.
Review source files changed during a phase for bugs, security issues, and code quality problems
Planner+Architect+Critic→consensus impl plan (≤3 rounds)
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
Run a gated software development lifecycle for a repo. Use for `/jig init` (understand the codebase and scaffold project memory), `/jig task "<request>"` (start an issue/bug/feature through spec→implement→test→review→ship), `/jig status`, `/jig config` (view/set/validate settings), `/jig memory-refresh`, and `/jig resume`. Triggers on "jig", "run the lifecycle", "start a task", "sdlc", "sdlc init/status".
Local vision CLIs: glance (describe/ask/OCR an image), ground (locate a target, pixel box), detect (element inventory), trace (image to SVG geometry), crop (cut a pixel box to a file), and scripts/html_shot.py (HTML file to image). Use for any task involving an image — questions, text, splitting and transcribing long screenshots or chat histories, locating elements, comparing, rebuilding as HTML/SVG, digitizing a sketch or diagram, reading values off a chart, operating a GUI from screenshots — and to re-check an image yourself when a description you were given lacks a detail.
Dolt-powered issue tracker for multi-session work with dependencies and persistent memory across conversation compaction. Use when work spans sessions, has blockers, or needs context recovery after compaction. Trigger with "create task", "what's ready", "track this work", "resume after compaction". Make sure to use this skill whenever managing multi-session work, tracking dependencies, or recovering context.
Reconcile session outcomes into persistent project memory files. Updates project state, backlog, and status via section-aware merging -- not a session dump. Use at the end of any significant work session. Use when: 'session close', 'close session', 'save session', 'update memory', 'wrap up', 'end of session', or before ending a big session.
Forge new Claude Code skills or optimize existing ones to V2. Two modes — `forge` scaffolds a new skill (frontmatter, progressive disclosure, helper scripts, mandatory Gotchas, iterate-then-extract); `optimize` makes an existing skill measurably better at its OUTCOME, not just its packaging (quality audit + domain outcome-research + changelog + V1-vs-V2 verification). Use when the user wants to create, write, build, scaffold, improve, upgrade, or optimize a skill.
All-in-one skill for CLAUDE.md files. Two modes: `audit` finds drift (claimed facts no longer matching code), leaked secrets, duplicates, instruction-budget bloat, and prescriptive-vs-descriptive imbalance across all CLAUDE.md files in your projects. `improve` measures one CLAUDE.md against Anthropic's official best practices (200-line budget, removability test, emphasis tuning, 3-tier hierarchy) plus community-validated guidance, then proposes concrete rewrite diffs applied only after user approval. Default behavior auto-detects: in a project with a CLAUDE.md → improve mode; otherwise → audit all. Use when: 'audit claude.md', 'check claude md drift', 'lint CLAUDE.md', 'claude md audit', 'refresh instructions', 'improve CLAUDE.md', 'restructure CLAUDE.md', 'tune CLAUDE.md', 'apply CLAUDE.md best practices', 'is my CLAUDE.md good', 'CLAUDE.md is too long', 'rebalance CLAUDE.md', or quarterly as a hygiene check.
(NS) Spec-driven delivery face — clarify, requirements, tasks (including unit/e2e test tasks), implement, resume or continue a version from disk artifacts. Entry priority 2: feature specs, version work, multi-day scope, or "continue" / "resume version" when partial artifacts exist under docs/versions/. Auto-sizes and runs internal phases via references/. Prefer ns-coder for bare quick fixes. Do NOT use for brownfield onboarding, architecture rules, or /ns-harness prepare (manual only; never auto-run Prepare).
(NS) Ad-hoc coding worker — bug fixes, small refactors, scripts, migrations — without full SDD. Entry priority 5: use for "just implement this", "quick fix", or concrete coding without execution-handoff (also C2 under ns-autonomous). Do NOT use for GitLab ISSUE_URL (ns-execution-gitlab-issue), multi-day/version scope (ns-spec-driven), diagnosis-only (ns-investigator), or when execution-handoff.md exists. Do NOT generate requirements/tasks/handoff.