agent-loom / rules

---
description: agent-loom full skill index — consult when selecting which skill matches the current task
alwaysApply: false
---

# agent-loom Skill Index (generated — do not edit by hand)

Generated by `gen_host_adapters.py` on 2026-07-08. 123 skills.
One line per skill: **name** — what it does / when to load it.
Open `.agents/skills/<name>/SKILL.md` to execute a skill's workflow.


## project-specific

- **agent-builder** — Design execution structure for decomposed processes: single agent or multi-agent topology …
- **agent-launcher** — Internal skill. Called by setup-evaluation after a PASS. Launches agents from a validated architecture spec using Claude Code / Ampcode native …
- **agent-loom-sync** — Sync library skills from an agent-loom upstream repo into this project's .agents/skills while preserving project-local and forked skills …
- **agent-observability** — Instrument a shipped product's AI agents with tracing and observability so you can see what they did, why outputs happened, and what each run cost …
- **agent-run-retro** — Run a structured retrospective after development-phase runs of your product's agents — interview the owner in plain language about what went well and …
- **agent-system-architecture** — Design state-of-the-art multi-agent systems, orchestration patterns, and wiring from scratch …
- **api-and-interface-design** — Design stable APIs and module boundaries — contract-first types, consistent errors, boundary validation, additive changes …
- **api-deprecation-and-migration** — Deprecate APIs, features, or systems safely — announce, migrate consumers, sunset on a timeline, and document alternatives …
- **app-security-hardening** — Harden an application against common security risks — validate inputs at boundaries, least-privilege access, safe secrets handling …
- **apply-paper-to-project** — Apply validated research paper insights to the current project codebase — improving architecture, code patterns, testing strategies, documentation …
- **architectural-decision-log** — Capture the "why" behind technical choices to prevent architectural drift …
- **browser-testing-with-devtools** — Test and debug browser UIs using Chrome DevTools MCP — DOM inspection, console errors, network requests, performance traces, and visual verification …
- **business-modeling** — Pick the right business-model canvas (Lean Canvas, Business Model Canvas …
- **ci-cd-and-automation** — Design and implement CI/CD pipelines and automation — fast checks on every PR, safe releases, and repeatable workflows …
- **code-review-crsp** — Review code changes for correctness, completeness, bugs, edge cases, and quality …
- **code-simplification** — Simplify application code for clarity without changing behavior — refactor after tests pass, reduce nesting and duplication …
- **codebase-understanding** — Quickly understand an unfamiliar codebase or project by mapping its architecture, identifying key components and data flows …
- **context-engineering** — Build the smallest, highest-signal context package for an AI coding task — goal, constraints, repo facts, boundaries, and a verification plan …
- **create-agent-prompt** — Create focused role prompts for agents in multi-agent topologies …
- **customer-discovery** — Run Mom Test–style customer-discovery interviews to validate or kill an unbuilt idea — generate a non-leading interview guide …
- **debug-and-fix** — Fix broken or failing functionality through structured reproduction, root-cause analysis, minimal fix, and verification …
- **dependency-mapping** — Map symbol dependencies, callers, and blast radius before editing code …
- **deploy-anywhere** — Deploy with unified build/test/deploy intent across providers using .agent-loom/deploy.yml and per-provider adapters …
- **design-direction** — Set a deliberate visual direction before any UI is built — the single biggest lever against generic AI output …
- **design-review** — Review a built frontend against its chosen direction, catch drift back to generic AI defaults, enforce state coverage, ethical patterns …
- **design-system** — Turn a chosen design direction into a canonical DESIGN.md plus production tokens that don't look vibecoded — state-level colors (8-step neutral ramp …
- **dynamic-routing** — Select alternative execution paths when a plan step fails — branch on outcomes instead of blind retry …
- **eval-judge** — Score LLM and agent outputs using LLM-as-judge techniques — direct scoring against rubrics or pairwise comparison between two outputs …
- **eval-output** — Orchestrator for the eval-output skill suite — evaluate LLM and agent outputs for quality, accuracy, helpfulness …
- **eval-pipeline** — Design automated evaluation pipelines for LLM and agent systems — combining deterministic checks, statistical metrics …
- **eval-rubric-design** — Design structured evaluation rubrics for scoring LLM and agent outputs — defining quality dimensions, scoring scales, hard gates, score descriptions …
- **experiment-backlog** — Turn assumptions, funnel opportunities, and product questions into a prioritised, feasibility-checked experiment backlog …
- **experiment-readout** — Analyse experiment results, run validity checks (SRM, exposure parity, data integrity, novelty/primacy), interpret causally …
- **experiment-runbook** — Translate an approved experiment spec into a launch runbook — platform binding (PostHog primary), feature flag setup, assignment unit …
- **experiment-spec** — Write a rigorous, decision-grade experiment spec — falsifiable hypothesis, primary metric, guardrails, randomisation unit, exposure definition …
- **experimentation** — Orchestrator for the experimentation skill suite — turn assumptions and product questions into rigorous …
- **fault-localize** — Find the earliest decisive failure in an agent run trace and propose an evidence-backed targeted repair …
- **feature-spec** — Write the executable feature specification — the WHAT and WHY artifact that agents and reviewers treat as source of truth …
- **frontend-design** — Orchestrator + builder for distinctive, production-grade frontends that don't look AI-generated …
- **generate-changelog** — Generate user-facing or internal release notes and changelogs …
- **git-workflow-and-versioning** — Structure git work with atomic commits, conventional messages, short-lived branches, and pre-commit hygiene …
- **gsap-animation** — Build GSAP JavaScript animations for web apps — timelines, scroll-driven motion, SVG draw/morph/path effects, and React integration with useGSAP …
- **harness-engineering** — Orchestrator for agent harness work — the setup that makes AI agents follow project rules and improve when they fail …
- **harness-evolution** — Improve agent reliability over time — diagnose why agents fail and fix the setup …
- **harness-generation** — Seed minimal agent harness v0 — manifest, eval checks stub, governance …
- **idea-evaluation** — Score an unbuilt business idea on desirability, viability, feasibility, distribution wedge, why-now, founder-market-fit, market size, alternatives …
- **idea-generation** — Generate 5–10 business idea candidates from a blank page or a founder's domain context — using pain mining, jobs-to-be-done …
- **implementation-plan** — Create a detailed, step-by-step implementation plan for a feature or project …
- **incremental-implementation** — Deliver multi-file changes in thin vertical slices — implement, test, verify, commit, repeat …
- **issue-sync** — Mirror issues and status across issue trackers with stable external-ID mapping to avoid duplicates …
- **knowledge-graph** — Build, update, and query a persistent project knowledge graph from skills, memory, docs, and code structure — stdlib Python only, no external tools …
- **memory** — Orchestrate persistent agent memory across coding sessions, repos, and tools …
- **memory-audit** — Audit project and global memory for bloat, stale decisions, duplicates, contradictions, unsafe content, missing provenance, broken routing …
- **memory-capture** — Capture durable project memory from work, debates, debugging discoveries, learned conventions, deferred options, and session outcomes …
- **memory-compact** — Compress bloated project or global memory while preserving decisions, rationale, revisit triggers, provenance, and active user preferences …
- **memory-decision** — Record durable project decisions with rationale, alternatives, assumptions, status, and revisit triggers …
- **memory-forget** — Delete, redact, or archive project and global memories when the user says forget this, delete memory, remove that preference, do not remember …
- **memory-handoff** — Write concise next-agent handoff summaries across sessions, tools, and coding agents …
- **memory-promote** — Promote project-specific memories into strict, small global memory only when they are cross-project, stable, useful, safe …
- **memory-recall** — Retrieve task-relevant project and global memory without loading everything …
- **memory-startup** — Load bounded working context at the start of a coding session …
- **model-selection** — Plan which model tier handles which work BEFORE execution begins — a high-cognition model deeply understands the problem, lays the foundations …
- **motion-animation** — Build Motion (Framer Motion) React animations — declarative motion components, variants, AnimatePresence, layout transitions, scroll effects …
- **performance-optimization** — Measure, profile, and fix performance bottlenecks — Core Web Vitals, backend latency, bundle size, and database queries …
- **pr-authoring** — Author pull requests with intent-separated commits, blast-radius disclosure, and verification evidence …
- **prd-writing** — Run a structured discovery interview and produce a complete, developer-ready Product Requirements Document …
- **problem-to-plan** — Tactical fast path: turn a small problem, bug report, edit request, or narrow refactor into three deliverables — a brief change-spec (docs/specs/) …
- **process-decomposer** — Decompose tasks into structured, outcome-defined process entries with complexity triage …
- **product-soul** — Write a Product Soul document — the strategic north star that sits above any PRD or feature spec …
- **project-constitution** — Author the project's non-negotiable engineering rules — the constitution that every feature spec, plan, and implementation must satisfy …
- **project-orchestrator** — Route user requests to the right skill, decompose complex work into parallel subagents, and manage project phase transitions …
- **project-setup** — Generate a tailored AGENTS.md for any new project by interviewing the user about their skill gaps, project goals, and tech context …
- **quickstart** — Guided first-run that produces a real verified win in under five minutes using the skill library on a seeded offline fixture …
- **reality-check** — Evaluate any project, product, or system's claims against its actual implementation — scoring each claim for truth, identifying architectural gaps …
- **retroactive-project-setup** — Bootstrap full agent infrastructure for an existing, already-coded project without modifying a single line of source code …
- **run-trace** — Append structured execution traces across operational, cognitive, and contextual surfaces with minimal overhead …
- **runtime-learning-loop** — Design a self-improvement loop for a shipped product's AI agents — production traces feed evals, evals feed improvement proposals (prompts …
- **safe-change** — Apply one logical code change with mandatory impact mapping, git snapshot, verification, and automatic revert on failure …
- **setup-evaluation** — Validate process decomposition and architecture design quality before execution begins …
- **shipping-and-launch** — Prepare safe production launches — pre-launch checklist, monitoring, staged rollout, and rollback …
- **skill-finder** — Find the right skill for a capability. Load when a user or skill needs to check if a skill exists for a given task …
- **source-driven-development** — Ground framework-specific implementation in official documentation — detect stack versions, fetch authoritative docs, implement cited patterns …
- **spec-crosscheck** — Hard readiness gate before implementation begins — cross-checks the constitution, feature spec, plan, and tasks for consistency, traceability …
- **spec-driven-development** — Orchestrator for spec-driven development (SDD) — the discipline of writing executable specs before code …
- **structured-planning** — Decompose multi-step work into a revisable subgoal plan with stable step IDs, checkpointing, and plan-ahead execution …
- **svg-creation** — Create handcrafted static SVG graphics and performant SVG animations — icons, illustrations, loaders, path-draw effects, morphing shapes …
- **technical-debt-audit** — Audit the project's technical health and identify "high-interest" debt …
- **test-driven-development** — Apply the Red-Green-Refactor cycle to software development. Load when the user asks to write code using TDD, create unit tests …
- **tool-finder** — Identify the right tool for a process step. Load when a user or skill needs to check tool availability, confirm CLI compatibility …
- **venture-exploration** — Orchestrator for the pre-decision business-idea lifecycle — generate ideas, model them, evaluate them, validate them with customers …

## thinking

- **adversarial-hat** — Put on the adversarial hat and systematically attack any document, plan, strategy, or idea to expose its weakest points before commitment …
- **assumption-mapping** — Surface every assumption embedded in a plan, strategy, or document, assess how critical and how validated each one is …
- **brainstorming** — Turn a rough idea into a fully approved design before any code is written …
- **deep-thinking** — Orchestrate one or more thinking frameworks to work through any problem, decision, document, or idea rigorously …
- **fermi** — Decompose an unknown quantity into 3-5 estimable factors and produce a defensible order-of-magnitude answer without needing precise data …
- **first-principles** — Strip a problem to its irreducible fundamental truths and rebuild the solution from the ground up — free from analogy, convention …
- **inversion** — Flip a problem, goal, or decision 180 degrees to find what forward thinking misses …
- **ooda** — Apply Boyd's OODA loop to navigate fast-moving, uncertain, or competitive situations — Observe what is actually happening …
- **pre-mortem** — Run a pre-mortem — imagine the project has already failed one year from now and work backward to find the root causes before they happen …
- **second-order** — Think through the consequences of consequences — not just what happens immediately, but what happens next, and next after that, across time …
- **socratic** — Break a stuck or complex problem into the smallest sub-question that, if answered …

## meta

- **compress-skill** — Compress an oversized SKILL.md to under 200 lines without losing effectiveness …
- **cross-link-skills** — Repair and verify cross-references between SKILL.md files after a skill is created, renamed, removed, or restructured …
- **deprecate-skill** — Gracefully retire a skill that is redundant, superseded, or no longer earning its place in the context window …
- **improve-skills** — Audit, improve, and compress every skill in the repo using live research …
- **learn-from** — Orchestrator for the learn-from suite - auto-detects source type (academic paper, GitHub repo, blog/web article …
- **learn-from-article** — Extract actionable insights from blog posts, web articles, and practitioner content - assess credibility, run security checks …
- **learn-from-chat** — Capture actionable learnings that emerge during conversation — when the agent or user discovers that a skill, a set of skills …
- **learn-from-paper** — Extract actionable skill knowledge from academic papers and research articles, assess credibility, run security checks …
- **learn-from-repo** — Extract actionable patterns, architecture decisions, code conventions, and skill-relevant insights from GitHub/GitLab repositories …
- **library-skill** — Automatically maintain skill library consistency whenever a structural change occurs — new skill added, skill renamed, skill deprecated …
- **prune-skill** — Critically audit agent skills and remove content that is outdated, disproven, model-specific, or based on poorly cited sources …
- **publish-skill** — Package and publish a skill to the skills.sh community registry, a public GitHub repo, or both …
- **research-skill** — Research a skill domain before building or improving a skill. Searches academic papers, practitioner blogs …
- **secure-skill** — Security audit orchestrator for agent skills — scans for prompt injection, data exfiltration, credential theft, supply chain risks …
- **secure-skill-content-sanitization** — Content sanitization and hidden-content detection for agent skill security …
- **secure-skill-repo-ingestion** — Security checks for repository ingestion — scans repos for poisoned examples, dependency and supply-chain attacks, file/path traversal …
- **secure-skill-runtime** — Runtime security for agent skills — prevents state corruption, skill overwrite attacks, denial of service …
- **skill-deconflict** — Detect and resolve naming collisions, overlapping intent triggers, and insufficient intent diversity across the skill library …
- **skill-routing** — Match a user request to the right skill using trigger matching, project context, and conversation history …
- **split-skill** — Reduce an oversized SKILL.md by checking whether an existing skill already covers the excess sub-workflow before creating a new child skill only when …
- **validate-skills** — Run a fast, read-only health check across all skills in the library and produce a structured quality report — without modifying anything …

## uncategorized

- **universal-skill-creator** — Design, build, validate, and ship cross-platform agent skills …