BC skill-eval
Measure whether a skill helps by comparing runs with and without it. Use when: reading skill A/B results or deciding to keep, revise or remove one.
Measure whether a skill helps by comparing runs with and without it.
As a process C 52/100 · Has gaps — References files that are not bundled: ../skill-builder/SKILL.md, scripts/probe-skill.sh, scripts/lib/codex-exec.sh
ProcedureGitHubSoftware developmentInfrastructureData and analyticstype and topics are labelled automatically from the skill text
This is a copy of a skill from another catalog; the rating counts the canonical one: skill-eval (boshu2/agentops)
How to improve
- The text references files that are not there: add them or drop the references.
For the model run — optional
- 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: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
missing-refreference to a missing file: ../skill-builder/SKILL.md - warning
missing-refreference to a missing file: scripts/probe-skill.sh - warning
missing-refreference to a missing file: scripts/lib/codex-exec.sh - note
frontmatter-keyunknown frontmatter key "practices" - note
frontmatter-keyunknown frontmatter key "skill_api_version" - note
frontmatter-keyunknown frontmatter key "hexagonal_role" - note
frontmatter-keyunknown frontmatter key "consumes" - note
frontmatter-keyunknown frontmatter key "produces" - note
frontmatter-keyunknown frontmatter key "context_rel" - note
frontmatter-keyunknown frontmatter key "output_contract"
Process rating: all ten parameters 52/100
Will not run. References files that are not bundled: ../skill-builder/SKILL.md, scripts/probe-skill.sh, scripts/lib/codex-exec.sh
- 0Tools and files. 3 referenced file(s) missing: ../skill-builder/SKILL.md, scripts/probe-skill.sh, scripts/lib/codex-exec.sh
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 9 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 100Steps. 19 steps
- 100Result and completion. Output format and completion criterion are stated
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3719 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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)
- +1No license
- +2Single-language instructions
- +3Description length 147: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 19 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +4Reference files are cited in the instructions (4 of 4)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 76.