AB what-did-i-lose-in-compaction
What did I lose in context compaction that I must not forget? What happened before my context was cut? Use this right after a compaction notice, at the start of a resumed session, when an earlier result seems missing from your context, and before retrying anything a summary says failed. Rebuilds from the local ledger what happened before the compaction: hosts contacted, what is blocked or rate-limited for you, failed actions, silent failures (tool said ok, wire said no), undelivered messages, routes that worked, and the last actions before the cut. Returns a MUST NOT FORGET list. Do not use as a general summary of a short session that was never compacted.
What did I lose in context compaction that I must not forget?
As a process B 70/100 · Nearly there — weak spots: inputs and preconditions, running it twice
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 70/100
- 0Inputs and preconditions. Does not say what the process needs to start
- 30Running it twice. 8 mutating operations with no state check
- 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
- 100Tools and files. No external tools needed
- 100Steps. 31 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1292 tokens
- 100Progress reporting. Reports progress
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 663: enough signal without eating the budget
- +4Structure: 7 headings
- +3Step-by-step instructions: 31 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.