All authors
Claude Skills by wrg32786
github.com/wrg3278670 skills2 installs112 views
- Agent FitnessTrack and surface sub-agent dispatch calibration ratios. Extract from JSONL transcript or read existing ledger. Per-agent clean/blocked/errored/partial trends.Votes: 0GitHub stars: 18
- Body CheckCompose the AIgent's body state by reading existing signals. Lazy compute. Never polled. Reports the five pressures + recommended reflex.Votes: 0GitHub stars: 18
- BriefGenerate a structured delegation brief for any taskVotes: 0GitHub stars: 18
- Caddy AuditQuarterly 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.Votes: 0GitHub stars: 18
- Caddy EnrollEnroll 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>".Votes: 0GitHub stars: 18
- Caddy ExplainWhen 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.Votes: 0GitHub stars: 18
- Caddy MuteMute a Caddy hint class for a window. Defaults to 4h auto-expiry. Classes — memory, context, body, routing, all.Votes: 0GitHub stars: 18
- Capsule CompactCompact 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.Votes: 0GitHub stars: 18
- CloseCommit the session to durable vault memory and prepare a clean resume pointVotes: 0GitHub stars: 18
- Codex AdapterRoute 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.Votes: 0GitHub stars: 18
- Cognitive UpdateConservative close-parity updates to GOAL_STACK, BELIEF_STATE, SELF_MODEL, and PROCEDURES. Writes only explicit or mechanically evidenced deltas; ambiguity means no write.Votes: 0GitHub stars: 18
- Comms SummarizeEcho'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.Votes: 0GitHub stars: 18
- Compact NoteMnemosyne'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.Votes: 0GitHub stars: 18
- Context CapsuleThe 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.Votes: 0GitHub stars: 18
- Context HygieneNightly context trim for ACTIVE_PRIORITIES and the dated SESSION_LOG schema. Archives before removal, uses content-hash compare-and-swap, and refuses unknown shapes.Votes: 0GitHub stars: 18
- Critique PlanHypatia'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.Votes: 0GitHub stars: 18
- DecideRun a decision through the 12-lens frameworkVotes: 0GitHub stars: 18
- Deep ReconRun extended multi-agent reconnaissance sessions. Use when asked to brainstorm deeply, explore ideas from multiple angles, or generate a structured recon document.Votes: 0GitHub stars: 18
- DiagnoseWhen 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.Votes: 0GitHub stars: 18
- DigestReview staged memory candidates from MEMORY_CANDIDATES.md. Surface each with promote/skip/supersede options. Does not auto-promote.Votes: 0GitHub stars: 18
- DreamEvidence-gated synthesis over recent operating evidence. Appends admitted lessons and a dated synthesis with propose-only improvement candidates.Votes: 0GitHub stars: 18
- EnvelopeClassify 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.Votes: 0GitHub stars: 18
- Find WeaknessHypatia'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.Votes: 0GitHub stars: 18
- First 10 MovesThe 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.Votes: 0GitHub stars: 18
- First WinThe 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.Votes: 0GitHub stars: 18
- Honesty CheckRun 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.Votes: 0GitHub stars: 18
- Humanize DocsTransform 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", "remo...Votes: 0GitHub stars: 18
- ImpeccableCreate 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.Votes: 0GitHub stars: 18
- Learn From FailureWhen a failure occurs, classify it, check for repetition, and produce a durable artifact that prevents recurrence.Votes: 0GitHub stars: 18
- LearnWhen 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.Votes: 0GitHub stars: 18
- Meta Improve VaultUnique project-local route to the canonical constrained self-improvement protocol. Accepts only operator-approved Dream candidates.Votes: 0GitHub stars: 18
- Meta ImproveCanonical constrained self-improvement protocol. Reads operator-approved Dream candidates and never self-merges or self-approves.Votes: 0GitHub stars: 18
- Nightly Close ParityUnique project-local fire verb for the seven-leg nightly close-parity pass. Proves and loads the canonical top-level skill.Votes: 0GitHub stars: 18
- Nightly Ledger CaptureDiscovers missing honesty, trust-decay, failure-mode, and decision-outcome entries from local evidence; stages judgment and permits direct mutation only after an executable oracle.Votes: 0GitHub stars: 18
- NightlyCanonical 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.Votes: 0GitHub stars: 18
- OpenBoot the session, load context from the vault, and surface what mattersVotes: 0GitHub stars: 18
- Operator SetupThe 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.Votes: 0GitHub stars: 18
- OrientWhen the user (or an agent) is confused about where something lives, who owns what, what the rules are, or what to do next, run this to load the canonical map.Votes: 0GitHub stars: 18
- PauseCreate a Capsule v2 with `status: paused` capturing full execution state for later resume.Votes: 0GitHub stars: 18
- Port SpecLyra'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.Votes: 0GitHub stars: 18
- PromoteTake 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.Votes: 0GitHub stars: 18
- ReconcileRead-only attention reconciliation. Computes actual seven-day project attention from daily notes against explicit Tier-1 intended shares.Votes: 0GitHub stars: 18
- Research DeepNewton'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.Votes: 0GitHub stars: 18
- ResumeThe 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.Votes: 0GitHub stars: 18
- Sandbox RoutingSELF-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.Votes: 0GitHub stars: 18
- Scout VaultEcho'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.Votes: 0GitHub stars: 18
- Self ReviewSpawn 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?"Votes: 0GitHub stars: 18
- Semantic SearchSearch vault notes by meaning using local embeddingsVotes: 0GitHub stars: 18
- SetupConfigure or reconfigure aigent-OS identity, priorities, authority, projects, people, and decision logicVotes: 0GitHub stars: 18
- Ship AdapterLyra'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.Votes: 0GitHub stars: 18