Skill rating
78 skills. The A–F grade combines safety (60%) and quality (40%); tests add a bonus. The rating refreshes automatically from open catalogs.
ManufacturingLogistics and warehouseProcurementQuality controlContact centreField serviceFinanceCustomer supportindustry shortcuts
| # | Grade | Skill | Score ▾ | Safety | Quality | Process | Tests | Popularity | Updated |
|---|---|---|---|---|---|---|---|---|---|
| 51 | C | Sanctioned lane for non-behavioral work — docs-only edits, dependency bumps, reverts. Type-scaled gates; no TDD demanded of prose. | 100 | 68 | D | — | ★ 145 | 30 h ago | |
| 52 | C | Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to /ca-fix, /ca-adr, or a no-action close. | 100 | 68 | C | — | ★ 145 | 30 h ago | |
| 53 | C | Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or /ca-feature. | 100 | 68 | D | — | ★ 145 | 30 h ago | |
| 54 | C | The sanctioned task-board mutator — add a queued task, start one (flips to in-progress and stamps the date, minting a dotted ID on pick-up), or mark an in-progress task done. The only blessed write to | 100 | 68 | D | — | ★ 145 | 30 h ago | |
| 55 | C | The test-first gate. Routed to by /feature (after the spec is approved), /fix, and /refactor before any implementation code is written. Six gated phases — obligation scan, red, green, obligation verif | 100 | 68 | C | — | ★ 145 | 30 h ago | |
| 56 | C | Brownfield back-fill — scout an existing codebase and populate .codearbiter/, then lock it initialized. | 100 | 65 | C | — | ★ 145 | 30 h ago | |
| 57 | C | Periodic multi-reviewer sweep of the whole codebase — surfaces a triaged checkpoint report. | 100 | 65 | C | — | ★ 145 | 30 h ago | |
| 58 | C | Verify the active host install, package, command ownership, enforcement, and harmless live-fire probe. Read-only. | 100 | 65 | D | — | ★ 145 | 30 h ago | |
| 59 | C | Greenfield decomposition interview — a layered interview that populates .codearbiter/ and locks it initialized. | 100 | 65 | C | — | ★ 145 | 30 h ago | |
| 60 | C | Author a new codeArbiter skill: prove the gap is real, get the spec approved, then write it. | 100 | 65 | C | — | ★ 145 | 30 h ago | |
| 61 | C | Vet a new or changed third-party dependency for license, provenance, and supply-chain risk before any install runs. | 100 | 65 | D | — | ★ 145 | 30 h ago | |
| 62 | C | Lightweight Q&A about the project — answer from context and return, no routing, no state change. | 100 | 65 | D | — | ★ 145 | 30 h ago | |
| 63 | C | Author a numbered, dated, user-attributed Architecture Decision Record under .codearbiter/decisions/. | 100 | 65 | C | — | ★ 145 | 30 h ago | |
| 64 | C | Fix a confirmed bug: a failing regression test first, then a minimal fix, then the rest of the tdd gates. | 100 | 65 | C | — | ★ 145 | 30 h ago | |
| 65 | C | The Socratic spec-refinement front of /feature, and the planning front of /sprint. Routed to BEFORE any code — it takes a one-line idea and drives it to an approved, concrete spec with testable accept | 100 | 63 | C | — | ★ 145 | 30 h ago | |
| 66 | C | Show the codeArbiter command catalog — the public command list and what each routes to. | 100 | 62 | D | — | ★ 145 | 30 h ago | |
| 67 | D | First of two same-named skills, used to prove within-collection dedup still works. | 100 | 43 | F | — | ★ 145 | 30 h ago | |
| 68 | D | Second of two same-named skills, used to prove within-collection dedup still works. | 100 | 43 | F | — | ★ 145 | 30 h ago | |
| 69 | D | A fixture skill named debug, colliding with the debug command/agent. | 100 | 43 | D | — | ★ 145 | 30 h ago | |
| 70 | D | A sample skill for fixtures — does one gated thing well. | 100 | 43 | D | — | ★ 145 | 30 h ago | |
| 71 | B | The deep, rarely-convened whole-codebase audit lane. Routed to when the user invokes /ca-tribunal. Seven gated phases — cost/model, map, roster dispatch, triage, report, approval+filing, telemetry. Co | 100 | 78 | F will not run | — | ★ 145 | 30 h ago | |
| 72 | B | The deep, rarely-convened whole-codebase audit lane. Routed to when the user invokes {{CMD:tribunal}}. Seven gated phases — cost/model, map, roster dispatch, triage, report, approval+filing, telemetry | 100 | 78 | F will not run | — | ★ 145 | 30 h ago | |
| 73 | B | The deep, rarely-convened whole-codebase audit lane. Routed to when the user invokes /ca:tribunal. Seven gated phases — cost/model, map, roster dispatch, triage, report, approval+filing, telemetry. Co | 100 | 78 | F will not run | — | ★ 145 | 30 h ago | |
| 74 | B | The deep, rarely-convened whole-codebase audit lane. Routed to when the user invokes $ca-tribunal. Seven gated phases — cost/model, map, roster dispatch, triage, report, approval+filing, telemetry. Co | 100 | 75 | F will not run | — | ★ 145 | 30 h ago | |
| 75 | C | Investigate-then-decide root-cause analysis for a defect whose cause is unknown. No code changes — exits to $ca-fix, $ca-adr, or a no-action close. | 100 | 62 | F will not run | — | ★ 145 | 30 h ago | |
| 76 | C | Exploratory spike on a throwaway branch — answer a named question with disposable code. Never merges; exits to a findings note or $ca-feature. | 100 | 62 | F will not run | — | ★ 145 | 30 h ago | |
| 77 | C | Deep, rarely-convened whole-codebase audit — eleven specialist lenses, a resumable on-disk audit log, findings filed as GitHub issues on approval. Expensive; estimates cost and STOPs before running. N | 100 | 62 | F will not run | — | ★ 145 | 30 h ago | |
| 78 | D | Report this absolute source path, then read the nested routine. | 100 | 37 | F will not run | — | ★ 145 | 30 h ago |