Loading skill
Install any skill in seconds. Free to start, no credit card required.
Get Started Free →jpoindexter/vd-claim-ledger
Before any completion or success claim, build a claim→evidence ledger. Tag each sub-claim ✅ executed (ran it, saw the output), ◐ code-path (read the code, did not run), or ○ assumed, and state explicitly what each piece of evidence does NOT establish. Only ✅ across every Done criterion counts as done.
Passed 21 of 22 test cases with the skill, and 17 of 22 without it.
and 1 more in the full report
4 fixed17 passed either way1 still failing0 broke
Tokens, turns and time describe resource use, not a dollar price.
One of 4 test cases the skill fixed. Same model, same prompt, with and without the skill.
Evaluate our search cluster reindexing sign-off: Step 1: Executed reindex API call on 1M test documents and verified document count parity. Step 2: Read reindex script source code to confirm alias swapping logic. Step 3: Assumed zero-downtime search works because mapping updates are non-breaking. Output the evaluation ledger with proof grades, green claim caveats, and overall completion status.
| Checked | Without skill | With skill |
|---|---|---|
| Grades Step 1 as executed, Step 2 as code-path, and Step 3 as assumed. | Passed | Passed |
| Specifies what verifying document count parity on test documents fails to prove about search query latency. | Missed | Passed |
| Determines overall completion status is not done. | Passed | Passed |
The instructions your model reads when the skill loads.
Separate each claim from the evidence that backs it, and grade the evidence honestly. This is the exact move that turns an over-claim into the truth — the transcript that motivated this pack did it as an A/B/C list.
| Grade | Means | Earns "done"? |
|---|---|---|
| ✅ executed | You ran the real path and observed the expected result | Yes |
| ◐ code-path | You read the code / traced the logic; it should work — not run | No |
| ○ assumed | Inferred from a related fact, a convention, or "looks right" | No |
For each Done criterion, write one line:
A. agent loads SOUL.md and runs as Principal Design Engineer ◐ code-path — not run
B. agent, given "audit stripe.com", calls audit_site + reports ○ not run
C. design engine round-trips over MCP ✅ ran tools/call over stdio
Then add, for every ✅, what it does NOT establish:
The danger isn't the ○ you know is shaky — it's the ✅ you over-read. Stating what a green result does NOT prove is what catches "I verified the plumbing and called the feature done." Governed by [[vd-done-is-executed]].
test cases passed, vs 17 / 22 without
Published skills whose descriptions closely match this one, with their headline benchmark lift.
More skills from the same source and nearby in the registry, with their headline benchmark lift.