BC cms-project-governance
Keep a drifting or half-finished project under control with one compact, conflict-checked delivery state, right-sized scope, bounded autonomy, and independent QA acceptance. Use for non-technical requirement guidance, Legacy Bootstrap, Small/Medium/Large sizing, Lite/Standard/Full governance, Controller-Developer-QC routing, Milestones, Work Orders, QA acceptance, drift recovery, target rebaseline, roadmap review, or reducing token and document overhead. Typical triggers include 项目做了一半 / 不知道该不该继续 / 范围蔓延 / 想加新方向 / 想重开一个项目, scope creep, we keep adding features, too many documents and no working code, docs outweigh code, governance overhead is too high, 治理内卷, which project should I kill, should I archive this, redefine done, change the target, rebaseline, is this really accepted, and we accepted it but never shipped. Also use for anti-involution doc budgets, archive discipline, stop-loss rules, Active Packet bootstrap, and accepted-but-never-released risk. For already-authorized ordinary coding loops, use agent-loop-engineering. For a one-time read-only verdict on a project you have not committed to yet, use project-lifecycle-navigator.
Keep a drifting or half-finished project under control with one compact, conflict-checked delivery state, right-sized scope, bounded autonomy, and independent…
As a process C 61/100 · Has gaps — weak spots: inputs and preconditions, failures and branches, consistency
How to improve
- Shorten the description to 1024 characters.
- 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: 31. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1151 chars, limit 1024
Process rating: all ten parameters 61/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 40Consistency. Frontmatter name (cms-project-governance) differs from the folder (coding-management-system)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, node) that frontmatter does not declare
- 100Steps. 58 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 3630 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- low 15 top-level sections: this looks like several domains in one skill
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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 1151: 120–800 characters recommended
- +1No license
- +2Single-language instructions
- +4Structure: 16 headings
- +3Step-by-step instructions: 58 items
- +3Output format is stated explicitly
- +4Has examples (5 code blocks)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 62.