AB what-did-i-actually-do
What do I believe I did, and what did I actually do? Did the things I told the user really happen? Use this before reporting a task as done, after a long session, and whenever you are about to say 'sent', 'published', 'fixed', 'installed' or 'verified'. Reads your own session transcript for success claims and checks each against the record: tool outcomes, outbound sends and their delivery, POST/PUT status codes on the wire. Lists every claim as SUPPORTED, UNSUPPORTED or CONTRADICTED and names failed actions you never mentioned. Returns exactly RECORD_MATCHES_CLAIMS, CLAIMS_EXCEED_RECORD, RECORD_EXCEEDS_CLAIMS or NO_CLAIMS. Do not use before any action has been taken.
What do I believe I did, and what did I actually do?
As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, running it twice, progress reporting
How to improve
- 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
- note
frontmatter-keyunknown frontmatter key "homepage"
Process rating: all ten parameters 66/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 30Running it twice. 13 mutating operations with no state check
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (web) that frontmatter does not declare
- 60Result and completion. Output format stated, no completion criterion
- 100Steps. 33 steps
- 100When it triggers. States when to use and when not to
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1400 tokens
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
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 675: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 33 items
- +3Output format is stated explicitly
- +4Has examples (1 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 91.