BB project-lifecycle-navigator
Audit a project you are unsure about and get a go, narrow, pivot, archive or stop recommendation, without writing code or changing governance state. Use when a non-technical user needs structured project guidance, a project is drifting, existing code needs a read-only audit, a recent delivery needs comparison with its current target, or new requirements may change scope. Typical triggers include 项目做了一半要不要继续, 我是不是该重开一个, 范围蔓延, 想加个新功能, I have too many projects, should I kill this one, 帮我看看这个仓库还能不能救, audit my codebase, is this project over-engineered, 定义一下 MVP, 怎样算做完, 止损, 归档, 这个项目还有价值吗, define MVP scope, scope creep, project drift, startup checklist, go or no-go, portfolio cleanup, and repository health audit. Also use for duplicate-copy detection, missing version control, hardcoded secrets in shipped artifacts, god-module and entrypoint-sprawl findings, and pre-commitment stop-loss rules. Produces bounded recommendations and handoffs without coding, self-authorizing work, changing governance state, or claiming QA acceptance. For ongoing governance with Work Orders, Milestones, and formal QA acceptance, use cms-project-governance.
Audit a project you are unsure about and get a go, narrow, pivot, archive or stop recommendation, without writing code or changing governance state.
As a process B 72/100 · Nearly there — weak spots: when it triggers, inputs and preconditions, progress reporting
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: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
description-longdescription is 1144 chars, limit 1024
Process rating: all ten parameters 72/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 100Tools and files. No external tools needed
- 100Steps. 62 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2901 tokens
- 100Running it twice. Mutating operations check current state
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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 1144: 120–800 characters recommended
- +4No input/output examples
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +4Structure: 19 headings
- +3Step-by-step instructions: 62 items
- +3Output format is stated explicitly
Quality base 70; lint remarks subtract, signals add up to 100. Result: 50.