Claude Skills
The open format is called Agent Skills and works in Claude Code, Codex, Cursor and other agents — most people know it as Claude Skills.
Every Agent Skill we could find on GitHub, deduplicated by content. 79 566 files from 1 758 authors, of which 61 913 are unique — the rest is the same skill repackaged into someone else's repository. For each one: what it weighs in tokens, whether it ships runnable scripts, and which MCP servers it needs.
Manages Aminet INDEX infrastructure: fetch, parse, cache, and incremental update of ~84,000-entry package database. Use when managing INDEX data, checking freshness, or parsing .readme files.
Selective Aminet package mirroring: single-package fetch, integrity verification, mirror state tracking, bulk download, and sync detection. Use when downloading, verifying, or managing mirrored packages.
Multi-layer virus scanning for Aminet packages. Signature-based detection, heuristic hunk analysis, boot block scanning, quarantine management, and scan orchestration. Use when scanning packages, checking virus status, or managing quarantine.
Validates knowledge pack content against runtime schemas: .skillmeta against KnowledgePackSchema, modules against ModulesFileSchema, activities against PackActivitySchema. Checks cross-pack references, learning outcome uniqueness, and file completeness. Use when validating pack content after generation.
Orchestrates knowledge pack content generation pipeline: batch scheduling, completion tracking, cross-pack dependency ordering, and validation triggering. Use when coordinating pack generation across phases 245-251.
Domain knowledge for 10 specialized subjects: philosophy, theology, physical education, nature studies, home economics, visual arts, music, trades, astronomy, learning to learn. Use when generating Specialized & Deepening tier pack content.
Electronics Educational Pack — routes queries to 15 modules covering Ohm's law through PCB design
Domain knowledge for 15 core academic subjects: math, science, technology, engineering, physics, chemistry, reading, critical thinking, problem solving, communication, history, geography, materials, business, statistics. Use when generating Core Academic tier pack content.
Reviews knowledge pack quality: educational accuracy, grade-level appropriateness, accessibility compliance, learning pathway coherence, assessment alignment, and parallel instruction pattern conformance. Use when reviewing pack content after validation.
Adversarial spec-compliance PR review — cross-references diffs against approved specs, verifies runtime claims against source, detects competing PRs, audits scope/convention compliance. Use before merging.
REST API design best practices. Use when designing APIs, choosing status codes, or creating endpoints.
Cascade the same edit pattern across N files safely. Use when applying the same refactor to multiple files (e.g. swap import paths across 11 scripts, rename a symbol, migrate a call signature). Detects the common-shape-across-files situation and turns an N-file cascade into a planned audit → apply → verify workflow instead of N sequential manual edits.
Use when the user asks to forge, scaffold, or author a new cartridge — content cartridge, department cartridge, or chipset bundle. Drives the cartridge-forge loop (scaffold → fill → gate checks → commit) via the skill-creator cartridge CLI.
Creates context handoff documents for session continuity. Use when ending sessions, switching tasks, or handing off work.
Reviews code for bugs, style, and best practices. Use when reviewing PRs or checking code quality.
Persist progress for long-running jobs (batched LLM calls, large ingestions, multi-hour syncs) so that a context reset, crash, or interrupt doesn't lose work. Use whenever a job iterates over N items and completing item K matters independently. Provides a resumable.mjs library pattern plus the skill's invocation heuristics.
Triggers for automatically invoking the decision-framework skill before irreversible or high-blast-radius operations. Use as a checkpoint: when a proposed action matches a trigger pattern, pause and run the appropriate framework (first-principles, inversion, decision matrix, second-order thinking) before proceeding. Prevents ad-hoc calls from becoming regret.
Thinking frameworks for decisions and problem analysis. Use when evaluating options, root causes, or prioritizing.
Crafts and generates professional conventional commit messages following Angular/Conventional Commits format. Use when committing changes, writing git commit messages, or when user mentions commit message.
Environment configuration and secrets management. Use when setting up .env files, managing secrets, or configuring environments.
Pipeline retirement protocol for completed work items. Implements a 7-stage validate-commit-push-submit-notify-cleanup-terminate pipeline with irreversibility after push. Done means gone.
> Pick among candidate outputs (code, configs, plans) by running them on diverse inputs and clustering by behavioural fingerprint, rather than by textual aggregation or log-probability. Activates when an executor returns multiple plausible candidates that need disambiguation, when output-majority voting would be the default choice, or when reviewing generated code that has not yet been validated. The 2026 evidence (Semantic Voting, arxiv 2605.08680v1) is that any execution-based selector dominates output-majority voting by 19-52pp; sketch-generated "majority vote on code", "select from N samples", "validate the generated output", "behavioural verification".
GSD tutorial, command reference, and workflow explainer. Explains what a GSD workflow command does before you run it. Activates when user is new to GSD, asks about commands, wants to understand workflows, or mentions preview.
> Use the moment a request is underspecified and you are about to act on an ASSUMED goal. Enumerate the candidate goals the request could mean, project two or more plausible goals lead to materially different actions or artifacts, ask exactly ONE targeted clarifying question; otherwise proceed on the most-likely goal and state the assumption in one line. Clarification is an evidence-producing action, not a delay — but one question, never an interrogation. Distinct from gsd-spec-phase (GSD-phase-bound, emits a heavy SPEC.md) and intent-router (fetch strategy, not goal disambiguation). Backed by agent goal-state inference (arxiv 2606.16813v1). Triggers on acting under an assumed goal when the request admits more than one materially different reading.
Safe file operation patterns. Use when performing bulk file operations or writing deployment scripts.
Use when GSD commands are failing or .planning/ artifacts look inconsistent. Run before any GSD execute-phase or verify-work attempt to catch cross-artifact mismatches early.
Traces decisions and requirements through GSD artifacts. Use when user asks "why did we...", "what happened to...", or mentions decision history.
Use when the user asks "what should I work on", mentions GSD phases, ROADMAP, or .planning/ artifacts. Routes to the correct GSD command for the current project state.
Interrupt controller converting polled to proactive agent execution. Per-runtime strategies, configurable thresholds, Deacon heartbeat supervision. Fights LLM passivity bias.
> Classify the information-need of a query and dispatch it to the appropriate retrieval or reasoning strategy. Use before read-side memory access, before multi-strategy retrieval, or any time you'd otherwise default to "one retriever for everything". Returns a strategy label, a token budget, and a retrieval depth so downstream handlers can be specialised. Backed by Pre-Route (arxiv 2605.10235v2) and MemFlow (arxiv 2605.03312v1), which together show LLMs possess latent routing ability elicitable via a structured prompt — and that externalising the routing decision improves small-model performance "intent classification", or any query whose ideal handling depends on what KIND of question it is.
Extract creative intent from images into executable build specs. Activates on images + build intent, "image to mission", "i2m", or capturing visual energy in code/design.
| Generate intelligence briefings for the planning dashboard. Use this skill whenever a request file appears in `.planning/console/inbox/pending/` whose `type` field starts with `intelligence.` (refresh_briefing, triage_finding, snapshot_diff, investigate_section, dismiss_finding). The skill reads the per-project KB at `.gsd/intelligence/intelligence.db`, synthesizes a briefing with a causal hypothesis + acknowledged uncertainty + confidence label and ranked moves, then writes the result back to the KB. Always trigger this skill for these request types — do not generate briefings manually.
> Use at write time to vector/embedding memory — Grove content-addressed insertion, chroma/pgvector upserts, memory-consolidation promoting session traces to MEMORY.md, or embedding externally-ingested content. Scores each candidate record against a fixed panel of sentinel queries and quarantines any record that would become the nearest neighbor of too many unrelated queries — a hub — whether from adversarial poisoning or accidental over-generality. This is the memory-record-side sibling of skill-injection-guardian (file-side) and the write-side complement of memory-use-warrant (read-side). Quarantine, never silently drop; a human reviews. Backed by the admission-time hubness gate (arxiv 2606.19692v1). Triggers on inserting into vector memory, consolidating memory, and embedding stranger content.
> Use before you shorten, compress, or rewrite the BODY of an existing SKILL.md or agent .md — the moment you are about to cut text to reduce length. First inventory the file's operational anchors (exact code / command / API snippets, fail-closed workflow guards, and rule / threshold statements), preserve every one, then judge the rewrite by expected downstream task cost (exploration, debugging, recovery tokens) rather than by the resulting line count. A shorter skill that strips an anchor makes the agent MORE expensive per task, so length is never the objective and rewrite is not compression. Backed by Preserving Operational Anchors When Compressing Agent Instructions (arxiv 2606.09421v2). Triggers on shortening or refactoring a skill or agent body.
> Run this appropriateness check the moment you are about to integrate a retrieved long-term memory — a Grove content-addressed hit, a chroma/pgvector neighbour, a memory-consolidation digest, or a MEMORY.md line — into a response, especially anything touching private origins, Fox Companies IP, credentials, or Center Camp / consent-governed content. It answers a question correctly-retrieved item should reach output. Relevance is not appropriateness — a perfect similarity match can still be a boundary violation. Default is behaviour but must not be surfaced. Backed by RBI-Eval (arxiv 2606.06055v1). Triggers on surfacing recalled sensitive memory into a response.
Emit Postgres.sql and SQLite.sql from a single schema spec so tools work across both drivers without duplicating DDL by hand. Use when designing a schema that needs to support both shared Postgres deployments and zero-config SQLite. Reduces two-file sync burden to a single source edit.
> Security hygiene for GSD's self-modifying skill and agent system. (.claude/skills/, .claude/commands/), modifying agent definitions (.claude/agents/), working with YAML configuration or chipset files, handling JSONL observation data (.planning/patterns/), processing community-contributed skills or chipsets, any file path operations that could involve user input, or when installing/updating project-claude configuration. Also activates for discussions about skill-creator security, trust models, or content hygiene.
Package conversation research into a GSD-ready mission package. Produces a three-stage Vision → Research → Mission pipeline as a LaTeX PDF following GSD/NASA SE methodology, designed to be handed to gsd-skill-creator for execution. Use this skill when the user has been discussing, researching, or brainstorming a topic and then asks to turn it into a research mission, research pack, mission package, or says 'package this as a mission', 'make this a research pack', 'turn this into a mission for skill-creator', 'create a research mission from this', or 'use the research mission skill'. The skill harvests findings, sources, and structure from the current conversation and any prior research, then produces the complete pipeline document. Also trigger if the user asks to 'create a research mission on [topic]' cold — in that case, conduct web research first, then package.
> Project state awareness and session recovery for GSD-managed projects. a break, the user asks "where did we leave off" or "what's the current state", before making substantial code changes (to check for existing plans), the user seems disoriented about project status, or when something seems off and STATE.md might have relevant context. Also activates when the user references .planning/ files, milestones, phases, or project progress.
> Use when parallel agents in a convoy or across git worktrees hit a write conflict on shared state — a git tree, a config, or a shared document — and you must decide whether the conflict is semantically real. Classifies each conflicting hunk as independent (keep both), redundant (pick one), or a genuine clash (escalate), instead of blind locks, abort-and-retry, or wraps an LLM judgment, defaults to escalate on any uncertainty, and unconditionally escalates any hunk touching .planning/, config, credentials, or safety-critical paths. Backed by CoAgent (arxiv 2606.15376v1). Triggers on write conflicts between parallel agents on shared repo state.
Conversational guide for using tools/session-retro/observe.mjs to capture friction, wins, corrections, decisions, gaps, tool-use, and checkpoints as they happen during a session. Use at session start (to kick off the log), at inflection points (to record events), and at session end (to archive and feed the retrospective generator).
> Use when reviewing, shipping, or regression-testing a SKILL.md and you hold one or more captured trajectories where that skill was actually loaded. Translates the skill's instructions into behavior constraints, then reports which were EXERCISED (coverage) versus untested, and flags any that were in-scope but VIOLATED (compliance) — a cheap single-trajectory test-adequacy gate. It surfaces untested instructions rather than auto-blocking, and escalates fail-closed only when a violation touches shared repo state, never-surface memory, or self-modification. Complements skill-counterfactual-audit (which measures EFFECT) and skill-causal-curation (which measures contribution); this one asks ADEQUACY. Backed by the agent-skill-coverage metric (arxiv 2606.20659v2). Triggers on skill review, ship gating, and regression-testing a skill against its trajectories.
> Audit a skill by running a paired probe — the same task once with the skill loaded and once without — segment both traces into goal-directed phases, align phases, and emit a SIP report (surface anchoring, template copy, excess planning, task recovery, off-task artifact). Use whenever a skill is created, modified, or proposed for retirement. shows a single skill can produce 522 measurable behavioural changes this skill", "is this skill helping", "retire skill", "before shipping skill", "behavioural impact of skill X", or any skill review event.
Use when the user asks to forge, scaffold, author, or ship a new skill or agent — the skill-creator's own namesake artifacts. Drives the skill-forge loop (create → fill → validate → critique → ship → publish) via the skill-creator CLI.
Use when authoring or reviewing a SKILL.md or agent .md and you need to detect and fix the four most common frontmatter defects — echoed or truncated triggers, tools written as a YAML array instead of a comma-separated string, a description outside the 1-1024 character bound, and a missing "Use when..." clause.
> Manages skill-creator integration with GSD workflows including skill loading, session observation, bounded learning guardrails, and pattern relevant skills are loaded first), starting or resuming a work session (to check for pending suggestions), the user asks about skills, patterns, or skill-creator status, performing code changes that might represent repeating patterns, the user corrects Claude's output (highest-signal observation), or when skill refinement, creation, or suggestion review is discussed. Critical for maintaining the adaptive learning layer.
> Before dispatching a multi-agent team, run a spectral diagnostic on the proposed communication graph and emit a (ρ, Δ, κ) coordination signature plus a pass/fail verdict against per-task-class thresholds. Builds the row-stochastic operator P from the team graph, computes the successor representation M = (I − γP)⁻¹, and ranks the topology for robustness (κ, condition number), consensus (Δ, spectral gap), and drift (ρ, spectral radius). Per Parks & Alharthi (arxiv 2605.11453), rank order on (κ, Δ, ρ) predicts coordination quality "dispatch the team", "team topology check", "before running the agents", "is this team configuration OK", "team pre-flight".
Generates test cases for functions and components. Use when writing tests or creating test suites.
Instruction dispatch pipeline for routing work items to available agents. Implements a 7-stage fetch-allocate-prepare-hook-store-launch-confirm pipeline with batch convoy mode, formula expansion, idempotent dispatch, and crash recovery.
Transform a user's builder vision into a complete, executable GSD mission package. Use this skill whenever a user has described what they want to BUILD (a product, tool, feature, system, educational pack, or ecosystem component) and wants it structured for GSD execution. Triggers include: 'structure this for GSD', 'make this into a milestone', 'turn this vision into a mission', 'package this up for Claude Code', 'create the mission files', 'I want to hand this to GSD', 'make me a mission package', or any request to decompose a described system into wave-based executable tasks. Also trigger when the user has a vision doc already written and needs mission decomposition. Prefer this skill over generic document creation whenever the GSD ecosystem is mentioned alongside building something.
Unit Circle Laboratory + sc-dev-team autonomous mission control. Provides human-in-the-loop automation layer, pipeline management, context lifecycle, stuck-state prevention. UC re-execution series and dev branch milestones. Adapted from uc-lab pattern for code plan/execute/verify/complete. Auto-activates during UC milestone work; trigger: user says 'bring up the dev team'.
> Use when you have captured session evidence — session-retro / session- observatory-live traces in .planning/patterns/, tool logs, correction records — and want to induce a reusable skill from it. Segments the traces into candidate skill units (an LLM judgment, not a deterministic parse) and structure, execution semantics, and runtime attachments (verification, safety, rollback, state). It emits a spec object, NOT a finished SKILL.md, and hands that spec to skill-forge. It sits between skill-integration (upstream frequency detector) and skill-forge (downstream author). Backed by Agent-Trace-to-Skill Induction (arxiv 2606.06893v1). Triggers on inducing a skill from captured traces, turning a repeated pattern into a skill spec, and preparing evidence for skill-forge.
Token budget tracking and enforcement for Gastown convoy-level execution. Hard limits with pre-execution checking, per-convoy and per-agent tracking, structured stop reasons.
TypeScript best practices and patterns. Use when writing TypeScript, fixing type errors, or working with generics.
GSD-OS bootstrap guide — from freshly unzipped directory to fully operational development environment. Covers prerequisite detection, workspace setup, service bring-up, magic level adaptation, error recovery, and the you-can't-break-it guarantee.
Composes three-part DACP bundles from skill library artifacts. Determines fidelity level, queries catalog, and records assembly rationale.
Load, validate, and use DACP bundles as structured execution context. Detects .bundle/ companion directories, validates integrity (manifest schema, fidelity, provenance), loads typed data, and builds ExecutionContext for receiving agents. Scripts are NEVER auto-executed. Use when processing incoming DACP bundles, interpreting .bundle/ directories alongside .msg files, validating bundle integrity, or building execution context from bundle payloads.
Deterministic git operations with state verification for skill-creator managed repos. Use when managing repos, branches, worktrees, or contribution workflows.
Guidance for verifying documentation accuracy against running OpenStack infrastructure. Use when detecting documentation drift, validating operations procedures against live systems, or confirming that runbooks produce expected results on the deployed cloud. Implements NASA Product Verification (SP-6105 SS 5.3) applied to documentation artifacts.
> Produce animated source control visualizations using Gource. This skill handles installation of Gource and ffmpeg, detection of repository metrics, preset-based configuration, single and multi-repo log generation, ffmpeg video encoding pipeline, headless rendering for server environments, caption generation from git tags, GitHub avatar resolution, and GSD output delivery. Use this skill whenever the user wants to visualize repository history, create a code evolution video, see project timeline animations, generate Gource videos, combine multiple repos into one visualization, or produce any kind of source control visualization. Also trigger when the user mentions "Gource", "repo visualization", "code history video", "project evolution animation", or asks to "show me what we built".
Claude Skills — questions
Answers built from the skills we actually parsed.