AF context-engineering
Build or initialize team-style project context directories for context engineering. Use when the user says “构建/初始化项目上下文”, “针对该项目构建上下文”, **or** in English phrases like “build/initialize project context”, “scaffold project context”, “set up project context docs”, “create project context”, “generate project context docs”, “initialize context engineering project”, “set up team context”, “build context workspace”, or asks to scaffold a project context under a specified target directory (default ~/clawDir/team).
As a process F 57/100 · Will not run — References files that are not bundled: references/entrypoints.md
How to improve
- The text references files that are not there: add them or drop the references.
- 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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: references/entrypoints.md
Process rating: all ten parameters 57/100
- 0Tools and files. 1 referenced file(s) missing: references/entrypoints.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 40Consistency. Frontmatter name (context-engineering) differs from the folder (context-engineering-for-projects-skill)
- 65Failures and branches. 3 branches
- 70When it triggers. States when to use, but not when not to
- 100Steps. 89 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Execution cost. Instruction body is 1480 tokens
- 100Running it twice. Mutating operations check current state
- low 10 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (30 tags): a typed call is more reliable
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
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +5Description quotes 10 example trigger phrases
- +3Description length 511: enough signal without eating the budget
- +4Structure: 18 headings
- +3Step-by-step instructions: 89 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.