github.com/Yeachan-Heo/oh-my-claudecode
| Skill | Added | Review |
|---|---|---|
agent-doc-discipline skills/agent-doc-discipline/SKILL.md Writing-time discipline for documents agents consume (the five surfaces, specs, tickets, .omc/skills/) — every rule checkable and carrying a why, steps before reference, one meaning in one home, no restating what the environment already says. Mandatory at drydock seed generation and the launch C5 sediment pass; opt-in for any other agent-facing doc edit. The companion of minimal-code-discipline: that one disciplines code, this one disciplines papers. | 65 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
ai-slop-cleaner skills/ai-slop-cleaner/SKILL.md Clean AI-generated code slop with a regression-safe, deletion-first workflow and optional reviewer-only mode | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
architect skills/architect/SKILL.md Settle types and module shape before cross-boundary code — competing designs explored in parallel, compared on API surface and invariants, decision recorded with rejected alternatives and an accepted-deviations register. | 60 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
architecture-survey skills/architecture-survey/SKILL.md Periodic architecture survey — walks the module graph and reports ranked deepening candidates (shallow modules, hypothetical seams, logic behind the wrong seam). Survey, not rescue: it finds candidates and hands them to the captain; it never refactors on its own. | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
arena skills/arena/SKILL.md Run N parallel candidates at one brief and synthesize: rubric-first framing, isolated fan-out, a cross-judge on a different model, criterion-by-criterion pick, hand grafting. When one attempt would lock in the wrong shape. | 64 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
ask skills/ask/SKILL.md Process-first advisor routing for Claude, Codex, Gemini, Antigravity, Grok, Cursor, or Muse via `omc ask`, with artifact capture and no raw CLI assembly | 58 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
ask-navigator skills/ask-navigator/SKILL.md Shipyard's navigator — chart a foggy effort (destination unclear, questions not yet stateable) into a map of decision tickets on the repo's issue tracker, then work the frontier one ticket per session until the way is clear, and hand the collapsed decisions to /launch as a mission brief. Wayfinding, not building: it produces decisions, never deliverables. | 63 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 453d3de | |
autopilot skills/autopilot/SKILL.md Full autonomous execution from idea to working code | 49 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
autoresearch skills/autoresearch/SKILL.md Stateful single-mission improvement loop with strict evaluator contract, markdown decision logs, and max-runtime stop behavior | 51 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
babysit skills/babysit/SKILL.md Drive an open PR to merge-ready on the watch-pr verdict policy — watch checks and review state, fix CI, address comments; never merges, rebases, or force-pushes. For 'get this green' or 'babysit PR #N'. | 63 Impact — No eval scenarios have been run Securityby Low Low-risk findings worth noting Version: 453d3de | |
benchmark-checklist skills/benchmark-checklist/SKILL.md Vet a measured number before reporting or acting on it: name the limiter, measure the claimed work, repeat with variance, rule out the observer, label every claim. For any speedup, regression, or score you are about to report. | 72 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
blast-radius skills/blast-radius/SKILL.md Map what a change could break beyond the diff — dependents found by search and AST, classified certain/likely/unlikely — and prove the certain and likely ones by running their checks. Before risky refactors or signature changes. | 70 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
cancel skills/cancel/SKILL.md Cancel any active OMC mode (autopilot, ralph, ultragoal, swarm, ultrapilot, pipeline, team) and clean up retired legacy state | 59 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
configure-notifications skills/configure-notifications/SKILL.md Configure notification integrations (Telegram, Discord, Slack) via natural language | 51 Impact — No eval scenarios have been run Securityby High Do not use without reviewing Version: 453d3de | |
debug skills/debug/SKILL.md Diagnose the current OMC session or repo state using logs, traces, state, and focused reproduction | — — — Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
deepinit skills/deepinit/SKILL.md Deep codebase initialization with hierarchical AGENTS.md documentation | 52 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
deep-interview skills/deep-interview/SKILL.md Socratic deep interview with mathematical ambiguity gating before explicit execution approval | 54 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
diagram skills/diagram/SKILL.md Use the smallest visual when prose must carry structure—control flow, call depth, module ownership, or change shape: pseudocode, call tree, component/file tree, Mermaid diagram, or diff. Skip it when prose already answers the question. | 75 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
drydock skills/drydock/SKILL.md Lay the keel of the shipyard harness in any repo — the 4-pillar shared environment (Context, Rules, Tools, Standards), seeded as two faces on day one (CLAUDE.md + GLOSSARY.md) with every other surface appearing on first use, so that every human and agent inherits the same design language and anyone can ship. Run once per repo; re-run with --check to audit drift. | 53 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de | |
execute skills/execute/SKILL.md Carry an approved task through to working, verified code | 56 Impact — No eval scenarios have been run Securityby Passed No findings from the security scan Version: 453d3de |