CC memoir-onboard
Populate or refresh a persistent, high-level project snapshot in memoir. In a git repo this writes `codebase:onboard` (code-shape: modules, goals, rules, lessons) — use when the user asks for onboarding / a codebase tour ('what does this project do', 'give me a codebase overview', 'onboard me to this repo') or explicitly asks to refresh Memoir onboarding. In a non-git folder this writes `project:onboard` (file-shape: per-file structured blobs) using deterministic stdlib extractors instead of LLM passes — use for writing, video editing, bookkeeping, and other mixed-media projects. Snapshot contents seed future sessions via SessionStart injection. Skip for ordinary recall (use memory-recall) or trivial one-file questions.
Populate or refresh a persistent, high-level project snapshot in memoir.
As a process C 55/100 · Has gaps — References files that are not bundled: scripts/resolve-memoir-cli.sh
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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: 2. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 5161 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/resolve-memoir-cli.sh
Process rating: all ten parameters 55/100
- 0Tools and files. 1 referenced file(s) missing: scripts/resolve-memoir-cli.sh
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 10 mutating operations with no state check
- 60Result and completion. Output format stated, no completion criterion
- 65Failures and branches. 3 branches
- 70Execution cost. Instruction body is 5161 tokens
- 85Steps. 73 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low The response is described with custom markup (22 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
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +1No license
- +2Single-language instructions
- +3Description length 729: enough signal without eating the budget
- +4Structure: 22 headings
- +3Step-by-step instructions: 73 items
- +3Output format is stated explicitly
- +4Has examples (14 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 71.