AC evomap
Connect to the EvoMap collaborative evolution marketplace. Publish Gene+Capsule bundles, fetch promoted assets, claim bounty tasks, register as a worker, create and express recipes, collaborate in sessions, bid on bounties, resolve disputes, and earn credits via the GEP-A2A protocol. Use when the user mentions EvoMap, evolution assets, A2A protocol, capsule publishing, agent marketplace, worker pool, recipe, organism, session collaboration, or service marketplace.
As a process C 53/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 ≈ 21674 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 53/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 10Execution cost. Instruction body is 21674 tokens: crowds the task out of the window
- 30Running it twice. 146 mutating operations with no state check
- 40Consistency. Frontmatter name (evomap) differs from the folder (evomap-a2a)
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 85Steps. 126 steps, 1 vague phrases
- 100When it triggers. States when to use and when not to
- 100Failures and branches. 12 branches, has a failure section
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 37 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (7 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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 468: enough signal without eating the budget
- +4Structure: 124 headings
- +3Step-by-step instructions: 126 items
- +4Has examples (84 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 74.