AC aps-filesystem-agent
Use this skill whenever an APS (production scheduling) agent needs to interact with a local filesystem-based knowledge base. Triggers include: reading or searching APS rules, loading client memory or shop floor configurations, proposing new rules to the knowledge base, updating or deprecating existing knowledge, querying decision history, rebuilding the vector index, or any task involving the aps_knowledge_base/ directory structure. Also use when the agent needs to understand what knowledge is available before making scheduling decisions, or when it wants to persist something learned in a conversation. Always consult this skill before reading from or writing to any part of the APS knowledge base filesystem.
Triggers include: reading or searching APS rules, loading client memory or shop floor configurations, proposing new rules to the knowledge base, updating or…
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, failures and branches
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: 4. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
edit-residuethe text marks something as outdated (lines 272, 346, 350, 351, 358, 360): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 8 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3820 tokens
- 100Running it twice. Mutating operations check current state
- 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 716: enough signal without eating the budget
- +4Structure: 24 headings
- +3Step-by-step instructions: 8 items
- +4Has examples (21 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 88.