Claude Skills by boshu2

Generate and validate repo docs, READMEs Triggers: "doc", "generate and validate repo docs", "doc skill".

Measure declared project fitness goals Triggers: "fitness", "check project fitness", "measure goals".

Write compact caller-authored session Triggers: "handoff", "write compact session handoff".

Name the skills reserved for people to Triggers: "human-only skills", "which skills must I run myself".

Generate evidenced opportunities or Triggers: "idea genie", "what should we build", "challenge this idea", "compare proposals".

Execute one bounded RED to GREEN experiment Triggers: "implement", "implement this bead", "run the experiment". Full plan-to-validation requests route to rpi.

Optionally analyze collections of durable Triggers: "learn from verdicts", "mine validation history".

meta_skill (ms) — the skill-search/load Triggers: "ms", "meta_skill", "skill search", "find a skill for", "load skill guidance".

Use NTM as an optional pane adapter for Triggers: "ntm", "tmux panes", "ntm robot state".

Classify a pending decision as reversible or Triggers: "is this a one-way door", "can we undo this", "should I just decide this", "the models disagree with me", before any auto-decided approval gate.

Distill repeated, evidence-backed expertise Triggers: "operationalize this", "turn this expertise into a reusable capability".

Test repeated implementation shapes against Triggers: "mine a recurring code pattern", "is this abstraction earned", "extract invariants from implementations".

Shape or refine the existing bead or caller Triggers: "plan", "discover and plan", "shape this goal".

Optionally test a retrospective causal Triggers: "postmortem", "causal retrospective", "test a retrospective hypothesis".

Optionally challenge a frozen plan with one Triggers: "premortem", "challenge this plan", "what could make this plan fail".

Use RCH once to offload a build or collect Triggers: "use RCH", "offload this build".

Compare a claimed state with observable Triggers: "reality check", "is this claim actually done", "compare claim to repo".

Answer a bounded question with current cited Triggers: "research", "investigate this question", "find evidence". (Investigating a repository routes to codebase-recon.)

Reverse-engineer an authorized repo, binary Triggers: "reverse-engineer X", "tear down Y", "what should we steal from Z", "evaluate competitor/upstream", "should we fork/adopt/build-native".

Pick the one AgentOps skill that owns a Triggers: "which skill covers this", "route this", "is there a skill for X", "what should I use here", or any request whose owning skill is not obvious.

Inspect disk pressure with SBH and run one Triggers: "check disk pressure", "run SBH".

Retired — its runtime-neutrality contract Triggers: none — not routable.

Author and tier behavioral probes for a Triggers: "measure this skill", "the probe came back INERT", "the control arm aces it", "harden this scenario", "is this skill actually doing anything".

Load only the standards relevant to a Triggers: "check standards", "which standards apply".

Report observable AgentOps evidence without Triggers: "status", "show AgentOps status".

Dispatch explicit disjoint packets exactly Triggers: "swarm", "dispatch disjoint packets", "parallel explicit tasks".

Mine caller-supplied usage history for Triggers: "mine toil", "find repeated operational work".

Operate the Agentic Coding Flywheel as a Triggers: "using flywheel", "agent flywheel".

Scaffold an explicit one-shot workflow Triggers: "build a workflow adapter", "scaffold a one-shot workflow".

Planted lint fixture for `scripts/skill-eval.sh`. Intentionally broken: this front matter omits `name`/`id` (missing required metadata), leaves the description empty, and hardcodes an AWS key (a secret) in the code block below.

A planted fixture that satisfies every blocking skill-eval rule so the gate passes cleanly.

Switch a caller-selected coding-agent account and report the observed identity. Triggers: "switch account", "rotate coding-agent account".

Use Agent Mail as an optional messaging and file-reservation adapter for explicitly coordinated writers. Triggers: "coordinate writers", "reserve files".

Operate explicit orchestrator, implementer, validator, and scribe roles through a caller-selected agent runtime. Triggers: "agent-native factory", "role-shaped agent panes", "persistent workers".

Use an explicitly selected AGY runtime for one provided packet or fresh validator context. Triggers: "agy", "antigravity", "AGY evidence".

Guard outcome work against process overhead. Triggers: RPI pre-Plan guard; explicit "full anti-ceremony audit" requests.

Front door for agent automation: choose inline, bounded fanout, reusable skill/workflow/gate, persistent agent-native workers, or explicit Gas City. Triggers: "build automation", "which orchestration shape", "should this use NTM".

Initialize explicitly requested, missing AgentOps documentation and optional verdict storage without taking over repository workflow. Triggers: "bootstrap AgentOps", "initialize AgentOps docs".

Mine past agent sessions for working prompts, decisions, and patterns (session archaeology). Triggers: "cass", "mine past agent sessions for", "cass skill".

Configure default Claude Code enforcement hooks and opt-in guard recipes. Triggers: "cc-hooks", "configure Claude Code hooks", "install hooks".

Reconstruct a repository as cited entry-to-test flows and bounded claims. Triggers: "codebase recon", "trace this codebase", "repository audit", "refresh the prior recon".

Run one caller-supplied Codex command non-interactively and capture evidence. Triggers: "run Codex headless", "capture Codex evidence".

Convert AgentOps skill formats. Triggers: "converter", "convert agentops skill formats.", "converter skill".

Compile or lint a persistent Mayor-style goal prompt that ratchets a bead graph through bounded RPI experiments toward one larger outcome. Triggers: "craft a goal prompt", "mayor goal", "goal-runner prompt", "lint this goal", "is this goal safe". (Shaping one experiment''s intent routes to plan.)

Handle blocked destructive commands and configure agent safety guardrails. Triggers: "dcg", "handle a DCG block", "configure agent safety guardrails".

Load the AgentOps language and bounded-context contracts when a term needs precise meaning. Triggers: "define this domain term", "check the bounded context".

Measure declared project fitness goals without recommending or applying work. Triggers: "fitness", "check project fitness", "measure goals".

Compatibility alias — renamed to fitness. Use fitness to measure declared project fitness goals. Triggers: "goals" (deprecated).

Name the skills reserved for people to invoke — where the runtime honors disable-model-invocation — and when to reach for each. Triggers: "human-only skills", "which skills must I run myself".

Generate evidenced opportunities or challenge an idea with sealed perspectives. Triggers: "idea genie", "what should we build", "challenge this idea", "compare proposals".