BC pulseflow
Maintain a Markdown task dashboard backed by agent-written append-only AI work logs, then sync a daily AI DONE TODAY section plus a weekly usage panel via heartbeat or on-demand refresh. Use when building or operating a reusable task system where: (1) human tasks live in a single NOW.md dashboard, (2) agents automatically append work records after each completed work unit, (3) heartbeat scans logs and refreshes the AI-derived sections, (4) a new workspace or vault needs initialization with templates, paths, and sync state.
As a process C 58/100 · Has gaps — weak spots: when it triggers, inputs and preconditions, running it twice
How to improve
- 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
- warning
frontmatter-yamlSKILL.md: the frontmatter is not valid YAML (YAML parse error: Nested mappings are not allowed in compact mappings at line 2, column 14: description: Maintain a Markdown task dashboard backed by agent-written append-… ^ ); fields were read line by line. The usual cause is a colon inside an unquoted value
Process rating: all ten parameters 58/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 16 mutating operations with no state check
- 60Tools and files. Uses tools (bash) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 60Failures and branches. 2 branches
- 85Steps. 85 steps, 1 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2082 tokens
- 100Progress reporting. Reports progress
- low 11 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)
- -5TODO / placeholder text left in the skill
- -32 of 11 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 528: enough signal without eating the budget
- +4Structure: 12 headings
- +3Step-by-step instructions: 85 items
- +3Output format is stated explicitly
- +4Has examples (9 code blocks)
- +4Reference files are cited in the instructions (7 of 15)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 73.