wrg32786
Useraigent-OS gives Claude Code fully autonomous memory and context management. It remembers across sessions, checkpoints itself, and manages its own context window so you never re-brief it. A free, open-source operator layer, not a chat wrapper.
Categories
Indexed Skills (52)
context-capsule
The capsule verb, invoked explicitly — reconcile from the live memory, write a resume-ready capsule, then stop. Mid-session checkpoint or completion capsule; a rolling best-effort version of the same write also runs automatically on every Stop event via daemons/stop-capsule-writer.mjs.
codex-adapter
Route ONE bounded, mechanical task to the Codex CLI as a non-Claude executor, under the same review-before-merge gate as any other agent-produced diff. Use when the user explicitly asks to hand a task to Codex, or names OpenAI Codex / a non-Claude executor for a mechanical change (rename a symbol across files, add a config entry, apply a scripted find/replace). Not for open-ended or strategic work -- that stays with the operating Claude session.
nightly
Canonical seven-leg nightly close-parity protocol. Eleven independently evidenced checkpoints cover synthesis, reconciliation, context hygiene, sweeps, heat, digest, runtime health, cognitive state, ledger capture/review, and vault sync.
resume
The resume verb, invoked explicitly — load the newest valid capsule by created_at, re-ground against live memory, then ACT on waiting_on. Mid-session or on explicit ask; the post-clear boot fires the same procedure automatically via daemons/resume-verb.mjs.
dream
Evidence-gated synthesis over recent operating evidence. Appends admitted lessons and a dated synthesis with propose-only improvement candidates.
reconcile
Read-only attention reconciliation. Computes actual seven-day project attention from daily notes against explicit Tier-1 intended shares.
cognitive-update
Conservative close-parity updates to GOAL_STACK, BELIEF_STATE, SELF_MODEL, and PROCEDURES. Writes only explicit or mechanically evidenced deltas; ambiguity means no write.
context-hygiene
Nightly context trim for ACTIVE_PRIORITIES and the dated SESSION_LOG schema. Archives before removal, uses content-hash compare-and-swap, and refuses unknown shapes.
nightly-ledger-capture
Discovers missing honesty, trust-decay, failure-mode, and decision-outcome entries from local evidence; stages judgment and permits direct mutation only after an executable oracle.
caddy-mute
Mute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.
compact-note
Mnemosyne's note compaction skill. Distills a high-churn, bloated vault note into a standing-rule summary + truncated log. Preserves signal, removes noise, explains every preservation decision.
critique-plan
Hypatia's plan critique skill. Takes a strategic plan, architectural decision, or proposal and returns adversarial pre-commitment review — strongest counterargument first, hidden assumptions surfaced, alternatives named.
humanize-docs
Transform AI-generated documentation into human-readable prose with personality. USE WHEN: Converting rigid AI docs (checklist spam, CAPS LOCK emphasis, perfect symmetric structures, template dumps) into flowing, conversational writing that feels colleague-authored. Different from /humanizer — that skill detects AI writing patterns (Wikipedia taxonomy). This skill does aggressive deformalization of document structure and flow. PRIMARY TRIGGERS: "humanize this doc", "make this readable", "remove AI patterns from doc", "add human touch to this" See also: humanizer skill for text-level AI pattern removal.
impeccable
Create distinctive, production-grade frontend interfaces with high design quality. Generates creative, polished code that avoids generic AI aesthetics. Use when the user asks to build web components, pages, artifacts, posters, or applications, or when any design skill requires project context. Call with 'craft' for shape-then-build, 'teach' for design context setup, or 'extract' to pull reusable components and tokens into the design system.
research-deep
Newton's multi-source deep research skill. Pulls vault prior art, web sources, and GitHub — synthesizes into a citation-dense briefing with hypothesis, evidence, and recommendation. Returns honesty ledger.
sprite-spec
Iris's sprite design specification skill. Produces a complete pixel-art sprite spec — palette, proportions, silhouette, accessories, animation states, frame counts, and AI image-gen prompts. Returns honesty ledger.
digest
Review staged memory candidates from MEMORY_CANDIDATES.md. Surface each with promote/skip/supersede options. Does not auto-promote.
meta-improve
Canonical constrained self-improvement protocol. Reads operator-approved Dream candidates and never self-merges or self-approves.
nightly-close-parity
Unique project-local fire verb for the seven-leg nightly close-parity pass. Proves and loads the canonical top-level skill.
ponytail
Forces the laziest solution that actually works, simplest, shortest, most minimal. Channels a senior dev who has seen everything: question whether the task needs to exist at all (YAGNI), reach for the standard library before custom code, native platform features before dependencies, one line before fifty. Supports intensity levels: lite, full (default), ultra. Use on ANY coding task: writing, adding, refactoring, fixing, reviewing, or designing code, and choosing libraries or dependencies. Also use whenever the user says "ponytail", "be lazy", "lazy mode", "simplest solution", "minimal solution", "yagni", "do less", or "shortest path", or complains about over-engineering, bloat, boilerplate, or unnecessary dependencies. Do NOT use for non-coding requests (general knowledge, prose, translation, summaries, recipes).
agent-fitness
Track and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.
body-check
Compose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.
capsule-compact
Compact a long capsule chain. Walks parent_capsule_id backward from a head capsule; if chain >= 5, summarizes oldest 3 into a chain-summary capsule. Manual invocation.
comms-summarize
Echo's comms polling skill. Read an inbox, channel, or message thread and return a structured unread summary — sender, topic, action required, and urgency. Read-only.
find-weakness
Hypatia's targeted weakness-finding skill. Given a specific claim, architecture, or decision, finds the single strongest objection and the hidden assumption most likely to be wrong. Sharper and faster than critique-plan.
port-spec
Lyra's spec-port skill. Takes a complete written specification and ports it into working code or a vault artifact. Confirms scope, reads the target, builds, returns honesty ledger.
scout-vault
Echo's vault traversal skill. Read-only graph walk — find all notes related to a topic, trace wikilink chains, inventory a directory, or spelunk a codebase for definitions and call chains.
ship-adapter
Lyra's adapter-shipping skill. Ports a schema, interface, or API contract from one shape to another — DB adapters, API client wrappers, data transformers. Bounded scope, honesty ledger on delivery.
close
Commit the session to durable vault memory and prepare a clean resume point
open
Boot the session, load context from the vault, and surface what matters
caddy-enroll
Enroll a skill into Caddy's index so it can be surfaced when the right prompt arrives. Use when a new skill is created, copied in, or when a skill needs updated triggers. Usage — "/caddy-enroll <path to SKILL.md>".
deep-recon
Run extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angles, or generate a structured recon document.
first-win
The day-one first-win menu. Three dead-simple, high-value tasks (two zero-dependency) that each put a real, usable artifact in the operator's hands in minutes, so the "ship something real" promise is met on day one and never waits on a connector or OAuth.
operator-setup
The AIgent first-run operator-business interview. Learn the operator's business in three plain questions, write the first memory, and play back a briefing that reads personal, not templated. This is the "it remembers me" moment. A distinct skill that LAYERS ON TOP of the base /setup (which is left intact), it does not replace it. The first-run flow (/start) calls this, not the generic /setup.
setup
Configure or reconfigure aigent-OS identity, priorities, authority, projects, people, and decision logic
start
The day-one first-run flow and the everyday home screen. On first launch, greet, run setup, then carry the operator into a real first win. On return, give a short briefing and action menu.
meta-improve-vault
Unique project-local route to the canonical constrained self-improvement protocol. Accepts only operator-approved Dream candidates.
semantic-search
Search vault notes by meaning using local embeddings
brief
Generate a structured delegation brief for any task
honesty-check
Run the volunteering ledger before declaring work done. Forces surfacing of what changed/didn't, what was noticed-but-not-fixed, what was guessed, and what tradeoffs were made on the principal's behalf. The standard - the principal should never be surprised later by something the agent knew at the time.
caddy-audit
Quarterly skill that walks the skill-index against the actual SKILL.md files on disk, reports drift (skills indexed that no longer exist, skills on disk that aren't enrolled, skills whose descriptions have changed since enrollment). Hardens the auto-enrollment pipeline against silent rot.
caddy-explain
When a [CADDY] hint fires and the principal is confused why, /caddy-explain walks the scoring transparently — which trigger matched, what points it earned, what the threshold was, what other skills were close. Pairs with the legibility thesis. Caddy's decisions should be inspectable on demand.
diagnose
When something feels off, type /diagnose and describe the symptom. The skill walks the seven-layer stack (kernel, skills, hooks, daemons, vault, doctrine, principal config) and reports which layer is most likely responsible. Caddy pattern applied to debugging.
envelope
Classify any incoming directive as Ship / Ask one focused question / Propose first. Forces a sharp decision instead of a multi-option survey to the principal. The default failure mode for agents is treating ship-work as ask-work (over-surveying) or treating propose-work as ship-work (rushing irreversible changes). This skill prevents both.
first-10-moves
The exact operational recon sequence for an unfamiliar codebase or unfamiliar area. Replaces "ask the human to clarify" with "read the code first." Most clarification questions are answered by 5 minutes in the relevant file - this skill enforces reading before asking.
frontend-slides
Create stunning, animation-rich HTML presentations from scratch or by converting PowerPoint files. Use when the user wants to build a presentation, convert a PPT/PPTX to web, or create slides for a talk/pitch. Helps non-designers discover their aesthetic through visual exploration rather than abstract choices.
learn
When the principal is in learning mode (reading a repo, watching a talk, processing a new tool), /learn takes a brief input and produces a structured note in vault/concepts/learning/ with category, modern-stack location, relevance verdict, and reconsideration triggers. Captures the value of every learning sweep without requiring it to immediately translate to building.
promote
Take a slice of the current conversation and promote it to a durable vault artifact — concept note, project update, person profile, or doctrine entry. Pairs with /close. /close writes the daily note (transient outcome record); /promote elevates specific insights to permanent vault content the framework can refer back to.
sandbox-routing
SELF-CORRECT tool choice. About to Read a long file just to extract one piece of info? Use a sandbox tool that returns only the summary. About to run a long shell command? Same. Sandbox keeps raw output OUT of context — only summaries land. Triggers when about to flood context with large output.
self-review
Spawn a reviewer subagent with 4-6 specific verification questions before declaring non-trivial code work done. Triggers when changes are >30 LOC, multi-file, hot-path, prompt-affecting, or genuinely uncertain. Bad asks produce bad answers — this skill forces structured verification questions, not "is this good?"
skill-audit
List every installed skill, when it was last invoked, how often, and whether the description still matches the trigger patterns the principal actually uses. Flags dead skills for retirement and frequently-needed-but-missing capabilities for skill creation. Pairs with Caddy.
decide
Run a decision through the 12-lens framework
Bio shown is the top-scored skill's repo description as a fallback — real GitHub bios land in a future update.