Verification before completion
Skill Tsurai7/agentic-playbook/skills/verification-before-completion
Require evidence before claiming work is complete, fixed, or tests pass. Use before commits, PRs, or any "done", "fixed", "works now", "should work", or "tests pass" statement.From its SKILL.md
npx -y skills add Tsurai7/agentic-playbook --skill verification-before-completionAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 0 stars0 stars. Stars are a popularity signal and not a quality one, but at this level it is likely that nobody has read this closely except its author, and you would be relying on your own review.
SKILL.md
1.3 KB, 256 tokens by cl100k_base, as published. Nobody here has run it
Verification before completion
No assertions without fresh verification evidence.
Gate
Do not claim completion until you have run the relevant check and seen successful output in this session.
Required evidence
| Claim | Minimum evidence |
|---|---|
| Tests pass | Test command output showing pass |
| Build succeeds | Build command exit 0 + output |
| Bug fixed | Reproduction steps pass after fix |
| Lint clean | Linter output on changed files showing zero errors |
Process
- Identify the command that proves the claim
- Run it (fix failures; do not lower the bar)
- Read output — confirm success, not absence of errors
- Only then state completion
Red flags — stop and verify
- Using "should", "probably", "seems to"
- Reporting success before running the command
- Trusting a prior run after code changed
- "I'm confident" without command output
Short form
CLAIM: [what you want to assert]
EVIDENCE: [command just run]
OUTPUT: [relevant success lines]
VERDICT: [claim supported only if output matches]
Keep this gate for every "done" statement.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most quality gates skills give in 256 tokens
Counted across 1,195 of the 2,094 authors here whose files we hold, read 2026-08-07
- Read the output and check the exit codein 54 of 1195, across 14 files
- Verify requirements using a line-by-line checklistin 53 of 1195, across 12 files
- Identify the verification command proving the claimin 51 of 1195, across 12 files
- Run the full verification commandin 50 of 1195, across 11 files
- Verify output confirms the claimin 49 of 1195, across 12 files
- Check version control diff after agent delegationin 46 of 1195, across 6 files
- State claim with evidencein 44 of 1195, across 4 files
- Run the test suitein 33 of 1195, across 26 files
- Keep state in memory by defaultin 27 of 1195, across 6 files
- Make prototype runnable with one commandin 26 of 1195, across 5 files
- Produce a verification reportin 25 of 1195, across 14 files
- Detect the package manager from lockfilesin 24 of 1195, across 5 files
Said here and by no other author read
- read the command output to confirm success
- rerun tests after any code change
- fix failures without lowering the bar
- confirm bug fixes using reproduction steps
- use the claim evidence output verdict format
Grouped from the skills themselves: near-identical wordings counted once, and counted by distinct author, so one author publishing three of these counts once. Length counted with cl100k_base; the agent that loads this file may tokenize it differently.