CD skill-autobench
Author an eval for an existing skill from its REAL usage history, not its spec. Mine invocations from the brain's conversation archive (conversations/) and per-harness session transcripts — a user correction after an invocation is the gold signal — then synthesize an eval_contract plus 4-8 replayable cases with honesty labels (SPEC-DERIVED vs HISTORY-IMPLIED) and stage the result at skills/<name>/eval/autobench-<date>.md as PENDING-HUMAN-APPROVAL. Never rewrites SKILL.md. Ships two guard companions: panel integrity (multi-model judging must prove each provider actually responded) and the fail-improve taxonomy (logged LLM-fallback cases convert to deterministic code over time).
Author an eval for an existing skill from its REAL usage history, not its spec.
As a process D 48/100 · Unfinished process — References files that are not bundled: ../conventions/brain-first.md, ../conventions/model-routing.md, ../conventions/agent-operator-protocol.md
How to improve
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 0
✓ No critical or high findings
Files scanned: 1. 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
missing-refreference to a missing file: ../conventions/brain-first.md - warning
missing-refreference to a missing file: ../conventions/model-routing.md - warning
missing-refreference to a missing file: ../conventions/agent-operator-protocol.md - note
frontmatter-keyunknown frontmatter key "triggers" - note
frontmatter-keyunknown frontmatter key "requires" - note
frontmatter-keyunknown frontmatter key "mutating" - note
frontmatter-keyunknown frontmatter key "writes_pages" - note
frontmatter-keyunknown frontmatter key "writes_to" - note
frontmatter-keyunknown frontmatter key "upstream"
Process rating: all ten parameters 48/100
- 0Tools and files. 3 referenced file(s) missing: ../conventions/brain-first.md, ../conventions/model-routing.md, ../conventions/agent-operator-protocol.md
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 2 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 35 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 2846 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 (8 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)
- +1No license
- +2Single-language instructions
- +3Description length 685: enough signal without eating the budget
- +4Structure: 13 headings
- +3Step-by-step instructions: 35 items
- +3Output format is stated explicitly
- +4Has examples (3 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 60.