arcasilesgroup

@arcasilesgroup source repo

66 skills
0 followers
6 hours ago last updated

▌
Watch · arcasilesgroup bundle
Watch a video (URL or local path) like an editor. Extracts scene-change frames, pacing metrics (cuts/min, shot length), and a dense 0-10s hook microscope; pulls transcript from captions or Whisper. Produces an ingest-ready `report.md` and, after answering the user, optionally auto-ingests the analysis into your Obsidian vault (configurable via `$WATCH_VAULT_DIR`) — tied to *why* the user watched it.

0
installs
▌
AI Nan Watch · arcasilesgroup bundle
Run the /watch video-analysis pipeline against the NaN Builders cluster (api.nan.builders) — whisper-large-v3 for transcription and qwen3.6 (multimodal) as the analyzing model. Use whenever /watch is invoked from a session whose provider is nan (omp, pi, OpenCode, Zed configured with baseURL https://api.nan.builders/v1), whenever NAN_API_KEY exists, whenever the user mentions nan.builders together with videos or transcription, or whenever a watch run hits Whisper 429/524/25MB errors. This is the NaN adapter; for other providers add a sibling skill (e.g. ai-groq-watch) and leave the core `watch` skill untouched. Covers provider gotchas (base URL, model ids, User-Agent), rate-limit pacing, the audio chunking strategy, frame token budgets for qwen3.6's 256K context, and the workflow for very long videos.

0
installs
▌
AI Pr · arcasilesgroup bundle
Creates and updates pull requests with governance: runs the commit pipeline, enforces pre-push gates, generates structured PR body from spec, watches and fixes CI until merged. Trigger for 'open a PR', 'submit this for review', 'I am ready for review', 'merge this into main', 'draft PR', 'update the PR'. Not for commit-only flows; use /ai-commit instead. Not for narrative review; use /ai-review instead.

0
installs
▌
AI Code · arcasilesgroup
Writes production code that satisfies stack-context standards on the first pass: interface-first design, backward-compatibility checks, lightweight self-review. Trigger for 'implement this', 'write the code for', 'add X to Y', 'build this function', 'make this work'. Not for tests; use /ai-test instead. Not for debugging; use /ai-debug instead. Not for refactoring; use /ai-simplify instead. Not for schema work; use /ai-schema instead. Not for executing an approved plan end-to-end; use /ai-build (the gateway).

0
installs
▌
AI Docs · arcasilesgroup bundle
Manages the documentation lifecycle: CHANGELOG, README, solution-intent architecture docs, external docs portals, and documentation quality gates. Auto-invoked by /ai-pr. Trigger for 'update the changelog', 'the README is stale', 'document this feature', 'docs portal needs updating', 'did we document all changes'. Not for blog or pitch content; use /ai-prose instead. Not for marketing collateral; use /ai-marketing instead.

0
installs
▌
AI Test · arcasilesgroup bundle
Writes tests, enforces TDD (RED-GREEN-REFACTOR), analyzes coverage gaps, defines test strategy across Python, TypeScript, .NET, Rust, Go. Trigger for 'add tests for', 'write a test', 'I need 80 percent coverage', 'plan my test approach', 'TDD this'. Not for failing tests where the fix is unclear; use /ai-debug instead. Not for AI reliability over time; use /ai-reliability-eval instead.

0
installs
▌
AI Board · arcasilesgroup bundle
Operates the project board (GitHub Projects v2 or Azure DevOps): discovers configuration after install (fields, state mappings, process templates) and syncs work-item state at lifecycle transitions. Trigger for 'set up the board', 'configure our ADO board', 'discover board fields', 'move this issue to in-review', 'update the board', 'mark as in progress', 'sync the work item state'. Two subcommands: `discover` (post-install configuration write) and `sync` (lifecycle state transitions). Auto-invoked via `sync` by /ai-brainstorm, /ai-build, and /ai-pr; fail-open. Not for backlog execution; use /ai-autopilot --backlog instead.

0
installs
▌
AI Issue · arcasilesgroup
Creates a project work-item (issue / task / story) on the user's configured board: routes by manifest `work_items.provider` (GitHub Projects v2 or Azure DevOps), composes title + body + labels, attaches to the active board, and confirms a clickable link. Trigger for 'open an issue', 'file a bug', 'create a task', 'add this to the backlog', 'log a work item'. Not for upstream framework bugs (use /ai-engineering-issue); not for board configuration (use /ai-board discover); not for committing code (use /ai-commit).

0
installs
▌
AI Learn · arcasilesgroup
Extracts lessons from merged PR review feedback by analyzing what reviewers caught, identifying missed checks, and writing entries directly to LESSONS.md. Trigger for 'the AI keeps doing X wrong', 'learn from this PR', 'what patterns did reviewers catch', 'update our standards from feedback'. Not for in-session observation; use /ai-session-watch instead. Not for skill-level rewrites; use /ai-skill-improve instead.

0
installs
▌
AI Media · arcasilesgroup bundle
Generates images, videos, and audio via AI models (fal-ai MCP): cheap iteration models, expensive production finals, cost-estimate before generation. Trigger for 'generate an image', 'create a thumbnail', 'make a voiceover', 'AI video', 'text to speech for'. Not for design composition; use /ai-visual instead. Not for animation specs; use /ai-animation instead.

0
installs
▌
AI Prose · arcasilesgroup bundle
Writes content (blog posts, pitch decks, sprint review summaries, architecture board reports, solution intent documents) with automatic audience targeting (developer/manager/executive). Trigger for 'write a blog post', 'pitch this', 'sprint review summary', 'architecture board doc', 'solution intent for'. Not for documentation artifacts like CHANGELOG or README; use /ai-docs instead. Not for marketing/social content; use /ai-marketing instead. Not for code-level explanations; use /ai-explain instead.

0
installs
▌
AI Start · arcasilesgroup
Bootstraps a coding session: loads project context and displays a welcome dashboard with recent activity, board items, and available commands. Trigger for 'hello', 'lets start', 'good morning', 'whats the status', 'get me up to speed', 'I am back'. Also invokable mid-session to re-bootstrap. Not for human onboarding; use /ai-onboard instead. Not for governance review; use /ai-governance instead.

0
installs
▌
AI Advise · arcasilesgroup
Proactive governance advisor — checks standards, decisions, and quality trends during development. Always advisory, NEVER blocks. Three modes: `advise` (post-edit), `gate` (pre-dispatch), `drift` (on-demand decision audit). Trigger for 'governance check', 'advise on this change', 'check for drift', 'is this aligned with active decisions', 'shift-left advisory'. Not for blocking gates — use /ai-verify. Not for narrative code review — use /ai-review.

0
installs
▌
AI Commit · arcasilesgroup
Runs the governed commit pipeline: auto-branches from protected, stages selectively, formats and lints, scans for secrets, gates docs, composes a conventional message, pushes. Trigger for 'commit my changes', 'save my work', 'push this to remote', 'stage these files', 'ship it'. Not for opening a PR; use /ai-pr instead. Not for branch hygiene; use /ai-branch-cleanup instead.

0
installs
▌
AI Schema · arcasilesgroup
Designs schemas, plans safe migrations with rollback scripts, optimizes slow queries with index recommendations, defines data retention and GDPR right-to-erasure policies. Supports PostgreSQL, MySQL, SQLite, MongoDB. Trigger for 'add a column', 'we need a migration', 'the query is slow', 'define a retention policy', 'GDPR compliance for data'. Not for application-layer ORMs without DB schema; use /ai-code instead. Not for security audits; use /ai-security instead. Not for infrastructure provisioning — no infra skill exists.

0
installs
▌
AI Slides · arcasilesgroup bundle
Generates zero-dependency self-contained HTML presentations with keyboard/touch navigation and viewport-safe layout. Three modes: new (from scratch), convert (PPTX to HTML), enhance (improve existing). Trigger for 'create a talk deck', 'pitch deck', 'workshop slides', 'convert my PPTX', 'presentation for the all-hands'. Not for static visual art; use /ai-visual instead. Not for marketing collateral; use /ai-marketing instead.

0
installs
▌
AI Sprint · arcasilesgroup
Manages sprint lifecycle: plans a new sprint from backlog, runs data-driven retros comparing planned vs shipped, checks mid-sprint goal status, generates sprint review presentations. Works with GitHub Projects and Azure DevOps. Trigger for 'start sprint planning', 'kick off the sprint', 'lets do the retro', 'what did we deliver last sprint', 'sprint goals check', 'generate the sprint review deck'. Not for daily standup; use /ai-standup instead. Not for solo PR retro; use /ai-learn instead.

0
installs
▌
AI Visual · arcasilesgroup bundle
Produces static visual design artifacts (posters, banners, flyers, branding, cover art, identity compositions) by composing named aesthetic philosophies into HTML/SVG, rendered to PDF/PNG. Trigger for 'create a poster', 'design a banner', 'branding visual', 'cover art for', 'identity composition'. Not for UI interfaces; use /ai-design instead. Not for animation; use /ai-animation instead. Not for presentation decks; use /ai-slides instead. Not for AI-generated photographs; use /ai-media instead.

0
installs
▌
AI Explain · arcasilesgroup
Explains code, concepts, patterns, and architecture with engineer-grade depth: 3-tier control (brief/standard/deep), ASCII diagrams, execution traces, anchored to real file:line references. Trigger for 'how does this work', 'why does it do X', 'trace through this', 'explain this pattern', 'walk me through'. Not for documentation artifacts; use /ai-prose or /ai-docs instead. Not for fixing code; use /ai-debug or /ai-build instead.

0
installs
▌
AI Onboard · arcasilesgroup
Onboards humans to a project: architecture tours, topic search, decision archaeology, structured new-team-member orientation. Read-only — never modifies code. Trigger for 'where does auth happen', 'what is the architecture here', 'history of this decision', 'onboard me to this repo', 'tour the codebase'. Not for agent session bootstrap; use /ai-start instead. Not for code-level explanation; use /ai-explain instead.

0
installs
▌
AI Standup · arcasilesgroup
Generates standup notes and status updates from actual git commits and PRs — never reconstructed from memory. Trigger for 'write my standup', 'what did I do today', 'what did I ship this week', 'status update', 'handoff notes', 'end of day summary'. Not for pitch or blog content; use /ai-prose instead. Not for sprint retrospectives; use /ai-sprint instead.

0
installs
▌
AI Support · arcasilesgroup
Investigates customer-reported issues with structure: reproduces, traces to code, documents resolution, builds a searchable knowledge base organized by ticket ID. Trigger for 'a user is reporting that', 'customer complaint', 'support ticket', 'investigate this bug report', 'search past support cases'. Not for production incidents; use /ai-postmortem instead. Not for internal dev bugs; use /ai-debug instead. Not for feature requests; open a GitHub Issue with the enhancement label.

0
installs
▌
AI Pipeline · arcasilesgroup bundle
Generates, evolves, and validates CI/CD pipelines for GitHub Actions or Azure Pipelines, enforcing SHA pinning, timeouts, secret handling, and concurrency policy. Trigger for 'set up CI/CD', 'add a deployment pipeline', 'is this workflow secure', 'check workflow policy', 'add a security scan to CI'. Not for running pipelines; that is the CI system's job. Not for governance audits; use /ai-governance instead.

0
installs
▌
AI Scaffold · arcasilesgroup bundle
Creates new ai-engineering skills or agents end-to-end: scaffold, TDD pressure-test, optimize description, register in manifest, sync mirrors. Trigger for 'create a new skill', 'add a slash command', 'the framework needs a capability for', 'build a new agent', 'scaffold a skill for'. Not for evolving existing skills; use /ai-skill-improve instead. Not for description-only optimization; use /ai-prompt-tune instead.

0
installs
▌
AI Simplify · arcasilesgroup
On-demand code simplification — guard clauses, method extraction, nesting flattening, dead code removal, conditional simplification. Behavior preserved; tests pass after every change. Scoped to operator-chosen files or current diff. No PR, no auto-commit. Trigger for 'simplify this file', 'reduce complexity here', 'clean up the in-flight diff', 'flatten this nesting'. Not for scheduled repo-wide sweeps — use /ai-simplify-sweep. Not for structural changes (file moves, renames) — use /ai-refactor.

0
installs
▌
AI Animation · arcasilesgroup bundle
Designs motion, transitions, and micro-interactions for UI components: spring animations, gestures, easing, staggers, scroll-triggered and loading/skeleton motion. Trigger for 'animate this', 'add transitions', 'micro-interactions for', 'gesture design', 'swipe to dismiss', 'easing for this', 'review this motion for polish'. Not for design systems; use /ai-design instead. Not for visual art; use /ai-visual instead. Not for testing animation code; use /ai-test instead.

0
installs
▌
AI Autopilot · arcasilesgroup bundle
Delivers large multi-concern specs and backlog runs autonomously: decomposes specs into sub-specs (or normalizes work items into a backlog DAG), deep-plans with parallel agents, builds a dependency DAG, implements in waves, runs a single final quality loop with one bounded quality-remediation pass (verify+guard+review on full changeset), delivers via PR. Trigger for 'implement spec-NNN end to end', 'autopilot this', 'autonomous delivery', 'decompose and ship', 'run the backlog', 'execute these GitHub issues', 'process the sprint backlog'. Invocation is the approval gate. Not for small or single-concern tasks; use /ai-build instead. Not for ambiguous requirements; use /ai-brainstorm first.

0
installs
▌
AI Ide Audit · arcasilesgroup bundle
Audits an IDE end-to-end (instruction surface, hooks, skills, agents, installer wiring) using strict file-evidence — never assumptions. Trigger for 'audit IDE support', 'is Copilot wired up correctly', 'check Claude Code integration', 'are there orphaned hooks', 'verify IDE setup'. Accepts Claude Code, GitHub Copilot, Codex, Antigravity, or all. Not for code quality; use /ai-verify instead. Not for security scanning; use /ai-security instead.

0
installs
▌
AI Marketing · arcasilesgroup bundle
Drives go-to-market execution and marketing content: blog posts for distribution, social crossposts, X/Twitter automation, platform-native content engines. Trigger for 'go to market', 'marketing plan', 'write a blog post to publish', 'crosspost to socials', 'content engine', 'post a thread on X'. Not for fundraising/investor materials; use /ai-fundraising instead. Not for internal docs; use /ai-docs instead. Not for sprint reviews or solution intent; use /ai-prose instead. Not for code explanations; use /ai-explain instead.

0
installs
▌
AI MCP Audit · arcasilesgroup
Audits MCP servers and skills on demand using LLM coherence analysis to catch capability drift and rug-pulls. Trigger for 'audit this skill', 'is this MCP safe', 'check coherence', 'detect rug-pull', 'snapshot baseline', 'mcp audit'. Three modes: scan (declared-vs-observed), audit-update (post-update diff), baseline set (anchor known-good). Not for runtime payload inspection; use prompt-injection-guard hook instead. Not for CVE scanning; use /ai-security instead.

0
installs
▌
AI Brainstorm · arcasilesgroup bundle
Forces rigorous design interrogation BEFORE any code: explores approaches, surfaces ambiguity, gathers evidence, produces an approved spec that becomes the contract for /ai-plan. Trigger for 'lets add X', 'how should we handle Y', 'whats the best approach', 'I am thinking about', 'what should we build for'. Not for existing approved specs; use /ai-plan instead. Not for execution; use /ai-build instead.

0
installs
▌
AI Governance · arcasilesgroup bundle
Validates framework compliance, ownership boundaries, risk acceptance lifecycle, and manifest integrity for regulated environments. Trigger for 'are quality gates enforced', 'who owns this file', 'formally accept a known risk', 'pre-release compliance check', 'governance report for auditors'. Not for code quality; use /ai-verify instead. Not for security scanning; use /ai-security instead — this validates governance process, not code content.

0
installs
▌
AI Postmortem · arcasilesgroup
Documents production incidents, outages, degradations, and near-misses using the DERP format (Detection, Escalation, Recovery, Prevention) with targeted interview questions per phase. Trigger for 'we had an incident', 'write up the outage', 'something went wrong in prod', 'postmortem', 'near-miss analysis', 'incident report'. Not for customer support investigations; use /ai-support instead. Not for internal dev bugs; use /ai-debug instead.

0
installs
▌
AI Spec Draft · arcasilesgroup
Produces a 14-section spec brief in `.ai-engineering/specs/drafts/<topic>-brief.md` so an operator can hand off a fully-researched problem statement to `/ai-brainstorm`. Trigger for 'draft a spec brief', 'put together a one-pager for this idea', 'research and write up the problem before brainstorming', 'capture the diagnostic for this work'. Not for executing the spec (use /ai-brainstorm → /ai-plan → /ai-build); not for ad-hoc notes (use /ai-note).

0
installs
▌
AI Fundraising · arcasilesgroup bundle
Drives fundraising and investor readiness: market sizing, competitive diligence, pitch decks, financial models, and investor outreach. Trigger for 'raise money', 'build a pitch deck', 'draft an investor cold email', 'market sizing', 'competitive research', 'financial model for the raise', 'warm intro to investors'. Not for growth/social content; use /ai-marketing instead. Not for sprint reviews or solution intent; use /ai-prose instead. Not for internal docs; use /ai-docs instead.

0
installs
▌
AI Prompt Tune · arcasilesgroup
Optimizes prompts, system messages, and skill descriptions using explicit-over-implicit, show-do-not-tell, and rationale-embedding techniques. Trigger for 'this prompt is not working', 'optimize this skill description', 'improve triggering', 'rewrite this instruction', 'CSO-optimize'. Pass `--skill name` to optimize any skill's description field. Not for creating new skills; use /ai-scaffold instead. Not for evolving the entire skill body; use /ai-skill-improve instead.

0
installs
▌
AI Constitution · arcasilesgroup
Interviews the operator to produce a project-identity CONSTITUTION.md (Mission / Stakeholders / Vocabulary / Prohibitions / Compliance gates / Anti-goals / Boundaries / Escalation / Language / Lifecycle phase). Trigger for 'set up the constitution', 'define project identity', 'who is this project for', 'what does this project never do', 'amend the constitution'. Not for AI-behaviour rules — those live in CANONICAL.md / AGENTS.md. Not for spec governance; use /ai-governance instead.

0
installs
▌
AI Session Watch · arcasilesgroup
Observes session corrections, recoveries, and workflow patterns silently, then consolidates them into project-local observations on demand. Trigger for 'start observing', 'learn from this session', 'consolidate observations', 'review what was learned', 'observe this session'. Listening mode is passive; review mode extracts and writes. Not for cross-project learning; use /ai-learn instead. Not for skill rewrites; use /ai-skill-improve instead.

0
installs
▌
AI Skill Improve · arcasilesgroup bundle
Improves an existing skill based on real project pain (prior eval corpora under .ai-engineering/evals/, Engram cross-session observations, LESSONS.md, decision-store, instincts, proposals) by analysing the failure pattern, rewriting SKILL.md, and emitting the proposed delta as a PR comment only — no auto-merge. Trigger for 'improve this skill', 'improve /ai-plan', 'make /ai-review better', 'optimize all skills', 'batch improve skills'. Accepts a single skill name or 'all' for batch mode. Not for creating new skills from scratch; use /ai-scaffold instead. Not for platform audit; use /ai-ide-audit instead.

0
installs
▌
AI Video Editing · arcasilesgroup bundle
Edits real video footage: cuts recordings into highlights, transcribes and structures raw footage, runs FFmpeg operations (trim, concat, reframe, normalize audio), creates Remotion overlays, prepares social-platform cuts. Trigger for 'cut this video', 'edit the recording', 'make a highlight reel', 'reframe for TikTok', 'transcribe this footage'. Not for generating videos from prompts; use /ai-media instead. Not for animation specs; use /ai-animation instead.

0
installs
▌
AI Branch Cleanup · arcasilesgroup
Cleans branches safely: switches to the default branch, prunes merged and squash-merged branches, syncs to remote, sweeps stale specs, rotates `.ai-engineering/runtime/` per retention policy. Trigger for 'tidy up', 'tidy branches', 'sync to main', 'delete old branches', 'start fresh', 'rotate runtime'. Auto-invoked by /ai-pr after merge. Not for committing changes; use /ai-commit instead. Not for code-level dead-code removal; use /ai-simplify instead.

0
installs
▌
AI Simplify Sweep · arcasilesgroup
Sweeps stale code complexity on demand via an /ai-simplify wrapper, gates the diff, and opens a draft PR for human review. Trigger for 'run the simplify sweep', 'simplification sweep', 'simplify pass'. Never auto-merges, never runs unattended. Not for in-flight feature work; use /ai-simplify instead. Not for security cleanup; use /ai-security instead.

0
installs
▌
AI Reliability Eval · arcasilesgroup
Measures AI system reliability over time by defining pass/fail criteria before implementation, running capability checks, and tracking regression via pass@k metrics. Trigger for 'how reliable is this', 'did my changes break anything', 'measure AI performance', 'define success criteria', 'eval this feature', 'check skill regression'. Not for code correctness; use /ai-test instead. Not for quality gates; use /ai-verify instead — evals measure AI task completion consistency.

0
installs
▌
AI Engineering Issue · arcasilesgroup
Files an upstream bug or improvement report against `arcasilesgroup/ai-engineering` (the framework repo) with strict seven-vector redaction, mandatory human confirmation, and an archived sanitized copy. Trigger for 'report this upstream', 'file an ai-engineering bug', 'this looks like a framework bug', 'tell anthropic / arcasiles about this'. Not for your own project's board (use /ai-issue); not for security disclosure (use the private channel listed in CONSTITUTION.md).

0
installs
▌
AI Resolve Conflicts · arcasilesgroup
Resolves git conflicts intent-aware: categorizes by type (lock files, migrations, generated, config, code), regenerates or merges per category, never blindly accepts. Trigger for 'I have conflicts', 'rebase failed', 'merge conflict', 'cherry-pick failed', 'unmerged paths'. Not for branch hygiene; use /ai-branch-cleanup instead. Not for committing the resolution; use /ai-commit instead.

0
installs
▌
AI Session Watch Sweep · arcasilesgroup
Consolidates the session-watch observation backlog on demand: runs /ai-session-watch --review, gates the result, and opens a draft chore PR for human review. Trigger for 'run the observation sweep', 'consolidate observations', 'session-watch sweep'. Never auto-merges, never auto-files work items, never runs unattended. Not for interactive review; use /ai-session-watch --review instead.

0
installs
▌
AI Security · arcasilesgroup bundle
Reasons about trust boundaries, authentication, data, dependencies, skills and supply chain, runs the scanners this repository already pins, and reports PASS, FAIL or INCOMPLETE with the command behind each one. Trigger for "threat model this", "is this auth safe", "review the trust boundary", "audit these dependencies", "can this skill be made to do something else". Not for judging a diff on its merits — use /ai-review, whose security lens does that. Not for accepting a risk — use `ai-eng accept`, which needs a named person, a reason and an expiry. It replaces neither the guards nor CI, and it never declares compliance with anything.

1
install
▌
AI Challenge · arcasilesgroup bundle
Grills a written specification from outside it: at most ten questions per round, one at a time, each anchored to the sentence it attacks and decided by executing the commands behind it. Trigger for "challenge this spec", "attack this decision", "is this spec true", "grill this before I approve it". Not for judging a diff — use /ai-review, which reads a change against a spec and cannot also be its accuser. Not for finding a cause in code — use /ai-debug. It never approves, revises or rewrites: it returns findings that carry a command, the author folds them into the specification, and a person decides what they mean.

1
install
▌
AI Visual Plan · arcasilesgroup bundle
Turns a plan — one written here, one pasted from a chat, one another agent produced — into the review surface the human actually reads: the plan's own Markdown, carrying visual blocks the renderer turns into diagrams, file maps, decision tables and open questions, handed over as one page whose link opens in the browser. Trigger for "make this plan visual", "I want to see the plan before I approve it", "turn this pasted plan into something reviewable". Not for writing the tasks themselves — use /ai-plan, which owns what the plan says. Not for judging what a change did — use /ai-visual-recap.

1
install
▌
AI Visual Recap · arcasilesgroup bundle
Turns a finished work unit — a branch, a commit range, a PR, the tasks of one plan — into the record a reviewer reads before the raw diff: one page whose file-tree and diff excerpts come from git itself, whose narrative says what changed and why, and whose link opens in the browser beside the digest of the spec it recaps. Trigger for "recap this PR", "show me what this branch changed", "the build is done, what did it do". Not for planning work not yet done — use /ai-visual-plan. Not for judging whether the change is correct — use /ai-review, which attacks the diff; a recap only ever shows what is there.

1
install
▌
AI Goal · arcasilesgroup bundle
Runs one request through the whole governed cycle in a single pass — research, spec, challenge, council, build, review, verify, security, audit, ship — and stops only to hand a person a tested thing to try. Your invocation is the standing approval; nobody else steps in until the end. The bar is the green gate plus an independent critic's verdict on the real artifact, looped until both hold. Trigger for "finish this without me, give me something to test", "run the whole gauntlet to a green gate". Not for one stage on its own — call that stage directly. Not for approving anything: you finish, then hand over.

1
install
▌
AI Note · arcasilesgroup bundle
Saves a finding that took real time to reach — a non-obvious behaviour, an integration trap, a workaround and the reason it is needed — as committed markdown, stamped with the commit and the file patterns it describes so that it can be detected as stale later. Searches those notes too. Trigger for "save this", "note that", "remember this", "we worked this out the hard way", "do we have notes on", "what did we find about". Not for project decisions — use /ai-spec, which is where a decision has its context. Not for documentation somebody reads to learn the system — that belongs in the repository's docs.

1
install
▌
AI Plan · arcasilesgroup bundle
Turns an approved spec into a numbered task list where every task names one file, one check that fails, and how to undo it. When the spec adds anything deployable, the plan must carry a CI/CD task and an observability task; they are not optional. Trigger for "break this down", "what tasks do we need", "let's start implementing", "the scope changed, re-plan". Not for exploring the problem — use /ai-spec. Not for writing the code — say go once this is approved. Not for judging what was built — use /ai-review.

1
install
▌
AI Ship · arcasilesgroup bundle
Lands the work: one commit per change, the changelog entry, a pull request that opens with what changed in plain words, the production-ready boxes ticked with the command that ticked each, the work item closed by a keyword in the body, and the branch cleaned up afterwards. Trigger for "ship it", "open a PR", "I'm ready for review", "commit this", "merge it". Not for judging the diff — use /ai-review first. Not for writing the spec — use /ai-spec. Not for finding the bug — use /ai-debug.

1
install
▌
AI Spec · arcasilesgroup bundle
Writes the governed record of a decision before code exists: evidence, the problem, three real options, one recommendation and self-challenge, assumptions, unresolved risks, observable examples and the authority for proceeding. Trigger for "let's add", "how should we handle", "what's the best approach", "I'm thinking about", "what should we build for", "write the spec". Not for turning an approved spec into tasks — use /ai-plan. Not for writing code — use /ai-plan after approval. Not for judging a diff — use /ai-review.

1
install
▌
AI Build · arcasilesgroup bundle
Executes one task of an already approved plan, red to green to refactor, as one logical change with a clean checkpoint that says nobody has reviewed it yet. Trigger for "implement task 3", "build this", "make the plan's next step work", "write the code for this spec". Not for deciding what to build — use /ai-spec, which is where an option is weighed and an authority recorded. Not for diagnosing a failure — use /ai-debug, which finds a cause at file:line. It does not widen scope, edit the approved plan, approve its own work, publish or deploy; when the plan stops being true it stops and says so.

1
install
▌
AI Cycle · arcasilesgroup bundle
Walks one request through the governed cycle by loading each stage's own skill body and following it — research, spec, challenge, council, then a brief a person reads. After that person says go, `ai-cycle build <NNN>` runs the second half: build, review, verify, security, audit, ship. Trigger for "run the whole cycle on this", "/ai-cycle build 021". Not for one stage on its own — call that stage directly. Not for approving anything: it stops at the brief and has no field in which an approval could be written.

1
install
▌
AI Debug · arcasilesgroup bundle
Finds the root cause of broken behaviour and names it at file:line, then writes the check that fails for that reason before changing anything. Also resolves merge and rebase conflicts by intent rather than by taking a side. Trigger for "it's not working", "this used to work", "I'm getting an error", "CI is failing", "why is X happening", "I have conflicts", "the rebase failed". Not for adding test coverage to working code — use /ai-review. Not for exploring an unfamiliar area — use /ai-explore. Not for designing the fix — once the cause is named, use /ai-plan.

1
install
▌
AI Write · arcasilesgroup bundle
Writes technical documentation for this repository: a README, a wiki page, product documentation, API docs or a technical post. Applies the framework's single writing standard (`.agents/skills/ai-report/references/documentation-writer.md`, spec 039) and verifies every document against the tree. Trigger for "write the README", "update the wiki", "document this API", "write a technical post about", "refresh the docs". Not for the changelog — use /ai-ship. Not for a spec or an ADR — use /ai-spec. Not for a finding — use /ai-note. Not for an issue — use /ai-report.

1
install
▌
AI Design · arcasilesgroup bundle
One gateway with four routes for creating, extending or redesigning a web, mobile, native or CLI experience: shape the work, build the system, opt into imagery, and verify the rendered result rather than the declared CSS. Trigger for "design this screen", "build the design system", "make this responsive", "check the contrast and the states". Not for judging whether a diff is merge-ready — use /ai-review, which owns that. Not for a decision that needs recording — use /ai-spec, because no design document substitutes for a spec, an MADR or the Solution Intent. It imposes no style and never requires generated imagery.

1
install
▌
AI Report · arcasilesgroup bundle
Reports a reproducible fault in this framework through `ai-eng report issue`: a payload closed to nine allow-listed fields, scanned for machine paths, personal data and secrets, written as a local gitignored draft, and shown as the exact bytes with their SHA-256 before anybody confirms anything. Trigger for "report this bug", "file an issue about ai-engineering", "the framework is broken", "send this upstream". Not for a fault in your own code — use /ai-debug, which finds a cause at file:line. Not for a vulnerability sent anywhere public: that routes to private disclosure and this command refuses the other way.

1
install
▌
AI Review · arcasilesgroup bundle
Judges a diff the way a staff engineer would: does it do what it claims, is it correct at its boundaries, is it safe, is it tested, and is there a smaller version of it. Never claims the result of a mechanical gate — those ran in CI and it says so. Trigger for "review this", "any issues with this", "is this merge-ready", "look over my PR", "what would you change". Not for running the gates — that is just check in CI. Not for finding why something is broken — use /ai-debug. Not for landing the work — use /ai-ship. Not for deciding a request that falls outside a declared boundary — use /ai-verify, because a decision that cannot classify itself reports CANNOT DECIDE and blocks, and a review is not where an out-of-boundary decision gets made.

1
install
▌
AI Verify · arcasilesgroup bundle
Runs the gate and the security lane and ticks each production-ready box beside the command that ticked it, or walks a spec's examples and marks each one against a real command. Trigger for "verify this", "is it ready", "tick the boxes", "does it do what the spec said", "check the acceptance criteria". Not for judging a diff — use /ai-review, which reads a change and this reads a claim. Not for finding a cause — use /ai-debug. It observes and never accepts: incomplete is the answer to every box and every example with no command pasted beside it. Not for deciding a request that falls outside a declared boundary — report CANNOT DECIDE and block, because a decision that cannot classify itself is not a decision this skill can take.

1
install
▌
AI Council · arcasilesgroup bundle
Reads one specification through five lenses that never see each other, then has them read each other anonymously to refute what does not hold and to name what every one of them missed, in one pass whose verdict the author writes into the specification. Trigger for "council this spec", "read this from several angles", "what is this specification missing", "pressure-test this spec", "stress-test this before I sign it". Not for attacking the claims a specification makes — use /ai-challenge, which executes its sentences; this asks what is absent. Not for judging a diff — use /ai-review. Not for recording what was decided — use `ai-eng decide`, which needs a named person. It concludes and it never grants: it may write a verdict and a recommendation, and it may not write an approval, a PASS, a gate result or an accepted risk.

1
install
▌
AI Explore · arcasilesgroup bundle
Answers questions about this repository by reading it, anchored to file:line, and tours an unfamiliar area for somebody who has just arrived. Trigger for "where does X live", "how does this work", "why does it do that", "what depends on Y", "walk me through", "map this module", "trace this import chain", "onboard me". Not for evidence from outside this repository — use /ai-research. Not for diagnosing a failure — use /ai-debug. Not for judging a diff — use /ai-review.

1
install
▌
AI Research · arcasilesgroup bundle
Finds evidence from outside this repository and reports it with numbered citations, or marks a claim [unsourced] and leaves it marked. Uses only the tools the client actually has: the local floor is always on, web search / Tavily / Exa run only when the client configured them, and NotebookLM deep research runs only when `notebooklm doctor` passes — an absent tool degrades and is named, never an error. Ends with three cited directions worth taking. Trigger for "what does the state of the art say", "compare the options for", "find sources on", "is this still true", "what do the docs say about". Not for questions whose answer is in this repository — use /ai-explore. Not for diagnosing a failure — use /ai-debug. Not for deciding what to build — use /ai-spec.

1
install

66 published skills