a-i--skills

Set up Cloudflare Turnstile end-to-end in a project: scan the codebase, create the widget via the Cloudflare API, deploy the managed siteverify Worker, write the frontend snippets, validate, and persist the skill. Load this when a user asks to add Turnstile, set up CAPTCHA, protect a form from bots, or fix a Turnstile integration. Mirrors developers.cloudflare.com/turnstile/spin.

Four-phase protocol for clearing accumulated drift between memory claims, CLAUDE.md citations, and on-disk reality. Detects stale citations, missing files, and orphan plans; classifies findings; emits proposed diffs; codifies prevention. Companion to closeout (closeout discovers orphans; this skill polishes them). Discovery ≠ remediation — Phase 3 emits proposed diffs only; constitutional doc edits require explicit conductor authorization.

Ingest a corpus of session logs (JSONL transcripts, chat exports) and extract a persona profile — vocabulary frequency, unique idioms and coinages, structural analogies — then synthesize an ideal_yearning and archetypal_pattern and append the result to a {persona_id}.lexicon.yaml. Triggers on "extract persona", "build a lexicon", "map the domain language", or any request to process conversation logs into a voice/vocabulary model.

Apply narratological scoring to a text, transcript, or recording transcript — rating contiguous spans for pathos, logos, ethos, kairos, and density — then extract the single highest-scoring contiguous block as the work's Natural Center, with a scoring table and justification. Triggers on "find the natural center", "extract the most dramatic moment", "what's the strongest passage", or pulling the peak block from a long artifact for a short, excerpt, or trailer.

Transform any data, document, deck, README, manifest, config, or report by (1) extracting every piece of dynamic information — names, links, statistics, costs, identifiers, dates, thresholds — into configurable variables instead of hard-coding, and (2) enforcing that every factual assertion carries at least two independent citations. Triggers on "remove branding," "make this reusable," "transmute this," "parametrize," "no hard-coded values," "configurable," "needs citations," "verify these claims," or any request to convert a one-off artifact into a parameterized template.

Scan rough markdown, session exports, or pasted prose and isolate each core intent into a structured prompt atom — classified as law, value, directive, constraint, question, or branch-vector — then rewrite it into machine-readable YAML frontmatter per the RAW → CLEANED/FORMALIZED → ELEVATED doctrine. Triggers on "prompt atom extraction pass", "atomize this", "formalize these prompts", or converting loose operator text into registry-grade atoms.

Decompose a system, repository, or architecture into four tiers — Macro (whole system), Bricks (components), Elements (conceptual primitives), Primitives (base operations) — reading target source plus its seed.yaml, then output a comparison table of the new system against existing substrates to expose reuse and overlap before anything new is built. Triggers on "boil down", "decompose into primitives", "recursive boil-down", or analyzing a new repo/architecture against what already exists.

Parse a session transcript into a structured Session Governance Index — an annotated bibliography of every file modified and commit made, internal-energy accounting (tool uses, estimated tokens), shipped-vs-tasked atom tally, and classification of missing items as Gaps or Vacuums. Triggers on "visibility-schema-substrate-sweep", "session cascade audit", "session governance audit", or any request to summarize what a session actually produced versus what it was asked to produce.

Conducts a full automated autopsy of the current workspace directory to map files, identifies structural issues, proposes a restructuring plan (the signal), and establishes unified governance using templates. Use this skill when a user asks to map, restructure, reorganize, or apply new governance to an existing messy repository.

Resolve and load any agent capability across the whole fleet from one place. Given an intent, finds the matching skill, command, or agent across Claude, Codex, Gemini, .agents, a-i--skills, OpenCode, and OpenClaw — then loads it through a single portal. Use for cross-agent skill discovery, "which agent has a skill for X", capability routing, or "find a skill that does Y" when capabilities are spread across multiple agent ecosystems.

Dry-run audit + targeted cleanup for shell command history. Currently wraps atuin (stats today, prune, dedup with dated preview artifacts); extensible to zsh/bash/mcfly backends. Always previews before applying — apply commands are echoed for the human to run, never auto-executed. Triggers on "/shell-history-hygiene", "audit atuin", "audit shell history", "clean shell history", "atuin prune", "atuin dedup", "shell history hygiene", "history cleanup". Replaces ad-hoc one-liners (e.g. `... | tee cmd > file.txt` which wrote two files, swallowed dedup output, and left a junk `cmd` file).

Comprehensive quality verification system for code changes with build, type, lint, test, and security checks

Use when substantive inline content delivered during a session lives only in the JSONL transcript and needs promotion to a durable, surface-discoverable, remote-backed artifact. Triggers on "persist this", "promote to a plan", "make this survive context exit", "engine log N", or when closeout flags a deliverable as "inline only — not file-persisted". Provides the four-phase extract → frontmatter → propagate → register protocol. Sibling to artifact-resurfacing (which reconciles citations pointing at nothing); this one rescues content that exists without citation.

Verify claims in a session/PR/transcript against on-disk reality. Produce a verification report (verified / false-positive / false-negative / partial) with explicit owners. STOP at verification — do not execute remediation without explicit approval.

Curated bundle of governance and quality skills for ORGANVM ecosystem management. Includes ecosystem autopsy and discovery, promotion readiness, onboarding flows, stranger testing, repository standards, verification, and coding standards. Use when establishing or auditing governance practices for repositories.

Orchestrate a full directory-graph autopsy across an ORGANVM workspace, then emit migration signals that unite repositories under canonical governance. Thin wrapper over organvm ecosystem + organvm irf + promotion-readiness-checklist. Triggers on auto-autopsy, map all directories, governance migration, ecosystem discovery, or "send the signal to unite" requests.

Self-improvement patterns for AI agents to learn from feedback, errors, and successful patterns across sessions

Session-end ritual that walks back through plans authored and atoms touched in this session, assigning each a closure status (DONE-NNN, IRF-XXX-NNN, or `~/.Codex/plans/abandoned/`). Verifies git state. Produces CLOSEOUT_SUMMARY.md. Triggers on "/closeout", "close out the session", "end of session", "wrap up", "session close", or before any planned `git push`. Addresses the 90.4% plan-orphan rate documented in docs/evaluation/self-review-2026-05-05/stale-plans-and-orphan-commits.md.

Wraps each surfaced dimension as a self-contained 9-section autonomous-work-assignment envelope — scope, context, success criteria, allowed tools, return format, handoff — all the recipient subagent needs to execute without coming back. Use when invoked by coliseum-orchestrator as Phase 2; when dimensions are named and the next step is to make each independently dispatchable; or when the user asks "compose this as an assignment." The no-pingpong gate validates each envelope before dispatch.

Dispatches a composed set of assignment envelopes to domain-expert subagents in parallel, in a single message with multiple Agent tool calls. Enforces the no-pingpong gate via the pingpong-detector agent before any dispatch fires. Use when invoked by the coliseum-orchestrator as Phase 3; when envelopes are already composed and the next step is parallel execution; or when the user asks to "fan out" or "dispatch in parallel." Produces a dispatch log capturing what was sent, when, and where returns land.

Threads the four-phase grain-to-coliseum transformation — given a dense prompt (the "grain"), autonomously surfaces parallel dimensions, composes self-contained 9-section handoff envelopes, dispatches in parallel, and reconciles returns into a composed whole under a mechanical compression gate. Use when a small-surface prompt plainly implies large scope; when the user invokes "grain → coliseum," "autonomous work assignment," "no ping-pong," or "chunk and hand off." Declines protocol when the grain is not fan-out shaped (≥3 independent dimensions).

Merges the parallel returns from a dispatched coliseum into a single composed whole — alchemy, not concatenation. Resolves tensions between returns explicitly, surfaces any BLOCKED records as named gaps, ensures no return is silently discarded. Use when invoked by the coliseum-orchestrator as Phase 4; when all (or recorded) returns from a Phase-3 dispatch are in and the next step is composition; or when the user asks to "reconcile," "compose the returns," or "merge into a whole." Produces the final artifact — phase-4-composed-whole.md — that closes the grain-to-coliseum loop.

Surfaces the parallel domain dimensions implicit in a dense or minimal prompt. Use when a user prompt is small on the surface but plainly implies multiple independent domains needing different expertise; when explicitly invoked by the coliseum-orchestrator skill as Phase 1; or when the user asks "what dimensions does this prompt encode" or "what axes does this break into." Produces a named dimension set where each dimension is independently executable and not a paraphrase of another.

Phase 5 of the pentaphase structural-overhaul protocol. Codifies operational protocols, onboards the ecosystem of participants, programs behavior monitoring, and establishes an iteration cadence so the substrate evolves rather than calcifies. Use when the user invokes phase 5 of an overhaul, asks to "establish governance" or "lock in the protocols", or has completed ingestion and is ready to declare the substrate operational. Consumes phase-4-ingestion-report.md; produces phase-5-governance-charter.md, which closes the protocol.

Phase 1 of the pentaphase structural-overhaul protocol. Inventories assets, maps current flow, identifies friction, and defines value metrics for any substrate. Use when the user invokes phase 1 of an overhaul, requests a baseline audit, asks to "discover the landscape" of a system, or wants to understand current state before redesigning. Produces phase-1-landscape-report.md.

Threads the full five-phase structural-overhaul protocol — landscape discovery, taxonomy design, environment configuration, systemic ingestion, governance evolution — for any substrate the user names. Use when the user requests a structural overhaul, system redesign, or end-to-end restructuring of a documentation system, asset registry, code monorepo, knowledge base, or operational workflow; or when they explicitly invoke the pentaphase methodology. Coordinates handoffs between phase-skills and seats validation gates between phases.

Phase 3 of the pentaphase structural-overhaul protocol. Translates the taxonomy model into objective technical criteria, evaluates candidate mechanisms or frameworks, instantiates the chosen architecture, and programs validation rules. Use when the user invokes phase 3 of an overhaul, asks to "select a system" or "configure the environment", or has a taxonomy model and is ready to choose technology. Consumes phase-2-taxonomy-model.md; produces phase-3-environment-spec.md.

Phase 4 of the pentaphase structural-overhaul protocol. Purges redundancies, enriches and aligns legacy entities to the new schema, executes phased ingestion into the new environment, and audits integrity. Use when the user invokes phase 4 of an overhaul, asks to "migrate the data" or "ingest into the new system", or has a configured environment ready to accept legacy entities. Consumes phase-3-environment-spec.md; produces phase-4-ingestion-report.md.

Phase 2 of the pentaphase structural-overhaul protocol. Classifies entities, standardizes attributes, establishes relationships, and designs the access framework. Use when the user invokes phase 2 of an overhaul, asks to "design the taxonomy" or "model the structure", or has completed a landscape audit and is ready to redesign. Consumes phase-1-landscape-report.md; produces phase-2-taxonomy-model.md.

Comprehensive document creation, editing, and analysis with support for tracked changes, comments, formatting preservation, and text extraction. When Claude needs to work with professional documents (.docx files) for: (1) Creating new documents, (2) Modifying or editing content, (3) Working with tracked changes, (4) Adding comments, or any other document tasks

Comprehensive PDF manipulation toolkit for extracting text and tables, creating new PDFs, merging/splitting documents, and handling forms. When Claude needs to fill in a PDF form or programmatically process, generate, or analyze PDF documents at scale.

Presentation creation, editing, and analysis. When Claude needs to work with presentations (.pptx files) for: (1) Creating new presentations, (2) Modifying or editing content, (3) Working with layouts, (4) Adding comments or speaker notes, or any other presentation tasks

Comprehensive spreadsheet creation, editing, and analysis with support for formulas, formatting, data analysis, and visualization. When Claude needs to work with spreadsheets (.xlsx, .xlsm, .csv, .tsv, etc) for: (1) Creating new spreadsheets with formulas and formatting, (2) Reading or analyzing data, (3) Modify existing spreadsheets while preserving formulas, (4) Data analysis and visualization in spreadsheets, or (5) Recalculating formulas

Create a scheduled task that can be run on demand or automatically on an interval. Distills the current session into a self-contained reusable prompt with cronExpression or fireAt, then calls the create_scheduled_task tool. Use when the user wants a recurring or one-time task scheduled — e.g. 'remind me every Friday', 'run this hourly', 'schedule a daily inbox check'.

Multi-perspective collaborative inquiry. Decomposes a topic into six cognitive lenses (Scope, Logic, Mythos, Bridge, Meta, Pattern) that operate as a chorus rather than a single voice, then synthesizes meta-patterns no single lens could find alone. MANDATORY TRIGGERS: 'expansive inquiry', 'multi-perspective inquiry', 'explore this from every angle', 'six-lens analysis', 'run a chorus on this'. STRONG TRIGGERS: 'help me think through X deeply', 'mythopoetic AND logical analysis'. Do NOT trigger on simple Q&A or failure-focused inquiries — use premortem for those.

Run a premortem on any plan, launch, product, hire, strategy, or decision. Assumes it already failed 6 months from now and works backward to find every reason why. Produces a revised plan with blind spots exposed. MANDATORY TRIGGERS: 'premortem this', 'run a premortem', 'what could kill this', 'future-proof this', 'stress test this plan', 'what am i missing here', 'find the blind spots'. STRONG TRIGGERS: 'poke holes in this', 'devil's advocate this', 'where will this break'. Do NOT trigger on factual questions or LLM Council requests. DO trigger when the cost of being wrong is high.

Reflective pass over your memory files — merge duplicates, fix stale facts, prune the index.

Comprehensive dramaturgical analysis of screenplays and scripts. Use when asked to analyze, break down, map, or provide feedback on a script. Triggers on requests involving beat mapping, act structure analysis, scene-by-scene breakdown, first-reader reports, production notes, or any comprehensive script coverage. Claude assumes combined roles of aesthete, dramaturgist, narratologist, art historian, cinephile, rhetorician, producer, academic, and first-reader.

Guided Cowork setup — install role-matched plugins, connect your tools, try a skill.

Foundational layer beneath PDE. Governs eight-strata substrate (ontology, lineage, constellation, gap-map, agent-fleet, production-stack, internal-magnet, external-contribution) plus four operators (selfish-altruistic loop, magnetic membrane, portfolio operator, reflexive operator) for any domain a flag pierces — chess, fitness, voodoo, education, design, taxidermy. Pre-instantiates engine reuse via Phase 0 portfolio audit and stretching-rack gap diagnosis.