AD cc-plugin
Claude Code plugin lifecycle management. cache - clean old cache versions (cleanup only — NOT for cache miss diagnosis) [cache.md], clustering - skill affinity scoring (coupling/dep/hook-ownership) → plugin bundle membership [clustering.md], create - plugin authoring guide (structure, plugin.json, components) [create.md], dev-reflect - reflect local dev repo into marketplace clone for pre-push testing [dev-reflect.md], hud - OMC HUD statusline (omcHud elements, omcLabel, wrapper sed fallback) [hud.md], marketplace - clone/list/update marketplace repos [marketplace.md], troubleshoot - cache miss/error, install fail, cache sync, HUD diagnostics — ALL plugin errors route here [troubleshoot.md]. "plugin", "marketplace", "plugin install", "plugin not installed", "cache miss", "cache error", "plugin error", "load error", "reload errors", "dev reflect", "plugin clustering", "bundle skills", "skill affinity", "OMC HUD", "omcHud", "omcLabel", "statusline", "[OMC#" triggers.
As a process D 44/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 0
✓ No critical or high findings
Files scanned: 13. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 44/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 8 mutating operations with no state check
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 482 tokens
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +3Description length 979: 120–800 characters recommended
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- +2Single-language instructions
- +5Description quotes 17 example trigger phrases
- +4Description says when NOT to use the skill
- +4Structure: 4 headings
- +4Has examples (1 code blocks)
- +3All 1 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.