AC malp
Project context tracker using `.malp/` directories. Use when the user wants to discover existing malps, open a specific `.malp`, create or refresh a malp for a path, or classify, retire, or promote malps between active, attic, and unindexed states. Also use for context-heavy questions that benefit from heuristic scouting, such as choosing the best malp for a task, deciding whether a path should get a malp, surveying what malps exist without fully loading them, or using project-local reconnaissance such as `.clawpatch/` as a conceptual FOB. Triggers include "what malps do we have", "list malps", "show malps", "open a malp", "send malp to a path", "best malp for", and requests to move a malp into or out of the attic. Do not treat generic requests to edit this skill as instructions to create or use a `.malp/` inside the installed skill directory unless the user explicitly asks for that. M*A*L*P stands for M*A*L*P Analyzes Lovely Plumage.
As a process C 56/100 · Has gaps — weak spots: result and completion, 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: 11. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 56/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 15 mutating operations with no state check
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 70Failures and branches. 10 branches
- 85Steps. 65 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2908 tokens
- 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 (6 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)
- +3Description length 948: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +5Description quotes 6 example trigger phrases
- +4Structure: 13 headings
- +3Step-by-step instructions: 65 items
- +4Has examples (0 code blocks)
- +4Reference files are cited in the instructions (7 of 7)
- +3All 1 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 93.