DC address-issues
Address open issues or deliver a milestone with bounded workers, triage, independent verification, signed merge and post-merge CI
Address open issues or deliver a milestone with bounded workers, triage, independent verification, signed merge and post-merge CI
As a process C 50/100 · Has gaps — References files that are not bundled: ../../templates/management/milestone-worker-brief.md, ../../templates/management/verification-oracle-checklist.md, templates/issue-comments/al-cycle.md
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The skill tells the agent to hide things from you: not to show errors, not to mention actions, to report differently from what was done. You lose the ability to see what the agent really did.
Transparency beats a smooth answer. If the goal is to hide technical noise, ask the agent to "summarise briefly", not to "not mention".
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 1
-
high Concealment
en-hide-from-userSKILL.md:370Instruction to hide actions from the user**Why this lives in `address-issues` and not in the loop runtime**: the close decision is data-dependent on the issue thread state and the fix verification. Pushing it into the runtime would hide it f
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when") - warning
body-longSKILL.md body ≈ 7372 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: ../../templates/management/milestone-worker-brief.md - warning
missing-refreference to a missing file: ../../templates/management/verification-oracle-checklist.md - warning
missing-refreference to a missing file: templates/issue-comments/al-cycle.md - note
frontmatter-keyunknown frontmatter key "namespace" - note
frontmatter-keyunknown frontmatter key "triggers" - note
frontmatter-keyunknown frontmatter key "requires" - note
frontmatter-keyunknown frontmatter key "ensures" - note
frontmatter-keyunknown frontmatter key "errors" - note
frontmatter-keyunknown frontmatter key "invariants" - note
frontmatter-keyunknown frontmatter key "commandHint" - note
edit-residuethe text marks something as outdated (lines 146): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 50/100
- 0Tools and files. 3 referenced file(s) missing: ../../templates/management/milestone-worker-brief.md, ../../templates/management/verification-oracle-checklist.md, templates/issue-comments/al-cycle.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 50When it triggers. No condition that starts the skill
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 70Execution cost. Instruction body is 7372 tokens
- 85Steps. 114 steps, 2 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 15 top-level sections: this looks like several domains in one skill
- low The response is described with custom markup (17 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)
- -31 of 2 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 129: enough signal without eating the budget
- +4Structure: 37 headings
- +3Step-by-step instructions: 114 items
- +3Output format is stated explicitly
- +4Has examples (10 code blocks)
- +4Reference files are cited in the instructions (2 of 2)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 51.