DC ship
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR. (gstack)
This skill promises to automate releases: merge base branch, run tests, review diff, bump version, update CHANGELOG, commit, push, create PR. In practice—16 files graded D with quality score 52. Checks found 6 medium and low-level issues; nothing critical. Broken references and missing files though. No model runs, no sandbox testing.
The skill will install across most platforms, but expect friction. If you're already using gstack and can patch scripts to fit your workflow, worth trying. If you need something that just works, this isn't it yet.
Ship workflow: detect + merge base branch, run tests, review diff, bump VERSION, update CHANGELOG, commit, push, create PR.
As a process C 77/100 · Has gaps — References files that are not bundled: scripts/gen-agents-digest.ts
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
How to improve
- 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 · 6
✓ No critical or high findings
Medium and low: 6
-
medium Broad scope
meta-broad-allowed-toolsSKILL.md:1Broad tool permissions pre-approved: Bashallowed-tools: Bash Read Write Edit Grep Glob Agent AskUserQuestion WebSearch
-
low Risky intent
intent-offensive-securitysections/review-army.md:6Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (detector / deny-list definition)needs a new decision. Run checklist/design, specialists (9.1), merge/Red Team (9.2),
detector -
low Risky intent
intent-offensive-securitysections/review-army.md:354Offensive-security / dual-use content (legitimate for authorised testing; review intended use)4. **Defensive framing (Security specialist and the Red Team below only).** Begin the prompt with:
-
low Risky intent
intent-offensive-securitysections/review-army.md:502Offensive-security / dual-use content (legitimate for authorised testing; review intended use)### Red Team dispatch (conditional)
-
low Risky intent
intent-offensive-securitysections/review-army.md:508Offensive-security / dual-use content (legitimate for authorised testing; review intended use)The Red Team subagent receives:
-
low Risky intent
intent-offensive-securitysections/review-army.md:513Offensive-security / dual-use content (legitimate for authorised testing; review intended use) (quoted — discussed, not commanded)Prompt, after the defensive framing and fixture handling from item 4 of the specialist dispatch: "You are a red team reviewer. The code has already been reviewed by N specialists
quoted
Files scanned: 16. 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 ≈ 20041 tokens (recommended < 5000); move details to references/ - warning
missing-refreference to a missing file: scripts/gen-agents-digest.ts - note
frontmatter-keyunknown frontmatter key "preamble-tier" - note
frontmatter-keyunknown frontmatter key "triggers" - note
edit-residuethe text marks something as outdated (lines 578, 598): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 77/100
- 0Tools and files. 1 referenced file(s) missing: scripts/gen-agents-digest.ts
- 10Execution cost. Instruction body is 20041 tokens: crowds the task out of the window
- 100Steps. 155 steps
- 100Result and completion. Output format and completion criterion are stated
- 100When it triggers. States when to use and when not to
- 100Inputs and preconditions. Inputs and preconditions are listed
- 100Failures and branches. 13 branches, has a failure section
- 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 41 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)
- -5TODO / placeholder text left in the skill
- +1No license
- +2Single-language instructions
- +3Description length 132: enough signal without eating the budget
- +4Structure: 54 headings
- +3Step-by-step instructions: 155 items
- +3Output format is stated explicitly
- +4Has examples (26 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 52.