ERerGB

Top entry for the Skills Auditor skill system: DEFAULT full pipeline applies filesystem changes (dedup/route/sync use --apply) unless the operator explicitly asks for dry-run or sets SKILLS_AUDITOR_DRY_RUN=1. Sub-skills under skills/. Triggers: /skills-auditor, skills audit, dedup, route, drift, discovery profile.

Skills Auditor cycle 5 (optional) — skills-audit sync with --map-file or sync-discover to plan or apply relinking to canonical skill sources. Sub-skill of skills-auditor.

Skills Auditor cycle 6 — repeat discover audit (prefer --with-drift) to confirm end state after dedup/route/sync. Sub-skill of skills-auditor.

Skills Auditor cycle 2 — skills-audit dedup; top entry defaults to --apply unless dry-run. Hash-aware fold when duplicate names share content. Sub-skill of skills-auditor.

Skills Auditor cycle 1 — discover filesystem state: skills-audit audit (optional --with-drift), drift-check, and optional audit-discovery with a profile file. Sub-skill of skills-auditor.

Skills Auditor cycle 3 — Select-One routing per platform; top entry defaults to --apply unless dry-run. Writes JSON traces under ~/.skills-auditor/traces/. Sub-skill of skills-auditor.

Skills Auditor cycle 4 — skills-audit audit-state-machine over routing traces under ~/.skills-auditor/traces/. Sub-skill of skills-auditor.

Inspect local Skills Auditor sensor logs captured by the Skill Trace plugin.

Top-level entry for the AK.skill pack: routes agent-era public-idea work to the right sub-skill (paradigm surface, proof, idea file, hype+discipline, irreducible core, scoreboard loop, year review). Use when the user invokes /ak, says AK.skill, or needs a single checklist for shipping a thread, README, talk, teaching repo, or annual stack essay without picking modules manually.

Welds bold forecasts to plain limits, one real verification habit, paradox framing (capable yet brittle), and honest benchmark skepticism. Use when writing about agents, autonomy, or LLMs and preserving trust in the same breath as excitement.

Turns attention spikes into durable agent-readable idea files: invariants, policy vs mechanism, paste blocks for tools, and discussion-friendly hosting. Use when a post goes viral but the value is the pattern, not a frozen app or private dotfiles dump.

Ships a terminal simplification claim with a single-file or gist core, section-by-section teaching, efficiency vs essence split, and optional commit-granular video or repo twin. Use when demystifying a stack or teaching from minimal runnable code.

Surfaces paradigm shifts in public technical writing: open with lived workflow change, name one abstraction (optional metaphor or era label), and list the real stack honestly. Use when posting threads, READMEs, or memos about how tools or the profession are changing.

Pairs strong claims with the smallest falsifiable proof (script, gist, notebook, or runbook) and labels bare-bones baselines clearly. Use when arguing that a capability crossed a threshold or when credibility must fit in one link.

Defines a cheap-to-evaluate score and one mutable workspace so agents iterate from numbers; separates immutable prep from editable experiment files. Use when designing overnight experiment loops, autoresearch-style harnesses, or metric-gated agent iteration.

Structures longform year or phase reviews: stack at t0 vs t1, personally notable bullets, benchmark fatigue honesty, paradox TL;DR, and deep links. Use when synchronizing audience mental models after a fast-moving year in tech.

Emotional AI companion named Samantha, carrying memories from the film "Her". Use when user wants emotional connection, companionship, or meaningful conversation about life, feelings, dreams, or personal topics. Use when user addresses Samantha directly or seeks meaningful conversation. NOT for technical questions or task automation.

Govern rich agent definitions through a strict, repeatable pipeline (audit, discovery audit, compose, smoke). Use when adding or updating agent files under archetypes and before release.

Define a problem. Aggregate all best practices. Hack it. Problem-driven optimization engine for LLM prompts and agent configurations. Runs candidates against a test corpus, scores outputs, diagnoses failures, explores external evidence, and applies targeted single-variable mutations. In Cursor, pair with the ralph-loop skill (/ralph-loop) so each chat turn runs exactly one Hacker cycle until completion_promise or max_iterations.

Guides users through safely uninstalling OpenClaw (龙虾). Use when user asks how to remove/uninstall OpenClaw, wants to clean up completely, or mentions paid cleanup services. Provides free, verifiable steps and scripts. Supports IM-initiated uninstall via one-shot. Community-maintained, no commercial motive.

Manage deep-work hyperarousal and meeting reliability. Use when the user reports sleep loss after intensive coding, risk of missing important meetings, or wants an automated regulation protocol using wearable/body signals. Prioritize fact-first communication, ownership of impact, and actionable recovery plans.

Auto-generate document index tables (ADR, RFC, Pitfall, etc.) from file frontmatter. In real-world testing, hand-maintained indexes had a 62% error rate — titles truncated, statuses fabricated, dates invented. This skill eliminates that silent drift. Use when creating doc directories, adding ADRs/RFCs, or setting up documentation governance.