Final review
Skill jsuvic/agent-profile/fixtures/tabnine-workflow-skills/expected/.agents/skills/final-review
Use before handing off an implementation to compare the diff against the spec, tests, docs, contracts, and safety rules.From its SKILL.md
npx -y skills add jsuvic/agent-profile --skill final-reviewAssembled from the repository path, not quoted from the project. Check it against their README if it does not work.
One thing to look at
- 3 stars3 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
0.8 KB, 135 tokens by cl100k_base, as published. Nobody here has run it
Final Review
Instructions
- Compare the implementation against the relevant spec.
- Confirm acceptance criteria are met or list the unmet criteria.
- Confirm tests and golden tests were run when applicable.
- Check generated outputs for deterministic formatting and intentional fixture changes.
- Check that no literal secrets, production access, unsafe auto-approval, source upload, or automatic dependency installation were introduced.
- Report remaining risks, TODOs, and documentation gaps.
Output
Return a concise final review with spec compliance, tests run, contract impact, security impact, and remaining risks.
What ships with it
Read from the repository
Just SKILL.md. No reference files, no scripts.
Gives 0 of the 12 instructions most review quality skills give in 135 tokens
Counted across 1,048 of the 1,783 authors here whose files we hold, read 2026-08-07
- Ask questions one at a timein 81 of 1048, across 64 files
- Provide a recommended answer for each questionin 73 of 1048, across 50 files
- Explore the codebase instead of asking answerable questionsin 66 of 1048, across 42 files
- Resolve dependencies between decisions one-by-onein 42 of 1048, across 17 files
- Interview the user relentlessly about the planin 38 of 1048, across 13 files
- Order findings by severityin 31 of 1048
- Resolve each branch of the decision treein 27 of 1048, across 5 files
- Run a grilling sessionin 26 of 1048, across 5 files
- Update CONTEXT.md immediately when a term is resolvedin 26 of 1048, across 11 files
- Propose precise canonical terms for vague languagein 25 of 1048, across 7 files
- Create documentation files lazilyin 24 of 1048, across 5 files
- Assign severity to every findingin 24 of 1048
Said here and by no other author read
- confirm acceptance criteria are met or list unmet
- confirm tests and golden tests were run
- check generated outputs for deterministic formatting
- check generated outputs for intentional fixture changes
- check no literal secrets were introduced
- check no production access was introduced
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.