doublecheck
Skill412 starsChanged 4 months agoApache-2.0View on GitHub
Cross-verify assertions, assumptions, and logic in code or explanations. Use as a quality gate before committing changes. Re-reads relevant code and confirms correctness.
7 other projects use a version of this.
Adopted by
Most recently taken up by
- github/awesome-copilottheir own version, first seen Oct 25, 2026
- poferraz/doublechecktheir own version, first seen Oct 25, 2026
- lacerbi/dotclaudetheir own version, first seen Sep 5, 2026
- ReaperOAK/ForgeOStheir own version, first seen Jun 8, 2026
- 5kuper/ai-docs-kittheir own version, first seen May 25, 2026
- arcobaleno64/council-forgetheir own version, first seen May 6, 2026
Other versions7 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 7
- github/awesome-copilot★ 41ksame name
- lacerbi/dotclaude★ 2same name
- 5kuper/ai-docs-kit★ 0same name
- arcobaleno64/council-forge★ 0same name
- poferraz/doublecheck★ 0same name
- ReaperOAK/ForgeOS★ 0same name
- snickerjp/Agent-Skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository8 other files it gives its agents.
- AGENTS.mdAGENTS.md
- .github/copilot-instructions.mdCopilot instructions
- ci-triageSkill
- codeql-scanningSkill
- code-reviewSkill
- package-removalSkill
- refactor-planSkill
- <skill-name>Skill
The file
Show its rules and text
We split this skill into the rules it gives an agent
15 rules. 0 are common, 13 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 7 edited versions we read keep these.
13
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Verify assertions, logic, and assumptions before finalizing changes.
- Distinctive: line 13
Before committing a non-trivial change
- Distinctive: line 14
After completing a debugging session
- Distinctive: line 15
When uncertain about edge cases or correctness
- Distinctive: line 16
When refactoring critical path code
- Distinctive: line 23
Check for off-by-one errors, null/undefined edge cases, and type coercion issues.
- Distinctive: line 25
Verify async code handles all Promise rejection paths.
- Very specific: line 29
Verify public-api.ts exports are correct and complete.
- Very specific: line 30
Check no test types are exported from public-api.ts.
- Distinctive: line 32
Verify Prettier formatting: double quotes, semicolons, 2-space indent.
- Distinctive: line 35
Run affected tests and confirm they pass.
- Distinctive: line 36
Check that tests are self-contained with injectable configuration.
- Distinctive: line 37
Verify test names describe expected behavior.
- Distinctive: line 41
Verify no circular dependencies introduced.
- Distinctive: line 43
Check imported modules actually exist and are correctly referenced.
“Common” is measured: kept by at least 6 in 10 of the 7 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Doublecheck Skill
Verify assertions, logic, and assumptions before finalizing changes. This skill provides a structured second-look workflow.
When to Use
- Before committing a non-trivial change
- After completing a debugging session
- When uncertain about edge cases or correctness
- When refactoring critical path code
Verification Checklist
Logic Verification
- Re-read the changed code and trace the logic step by step.
- Confirm all conditional branches produce the correct outcome.
- Check for off-by-one errors, null/undefined edge cases, and type coercion issues.
- Verify async code handles all Promise rejection paths.
Convention Compliance
- Confirm
Iprefix on interfaces,isIprefix on type guards. - Verify
public-api.tsexports are correct and complete. - Check no test types are exported from
public-api.ts. - Confirm no files under
generated/were modified. - Verify Prettier formatting: double quotes, semicolons, 2-space indent.
Test Verification
- Run affected tests and confirm they pass.
- Check that tests are self-contained with injectable configuration.
- Verify test names describe expected behavior.
- Confirm test files use
*.test.tssuffix and correct directory.
Dependency Check
- Verify no circular dependencies introduced.
- Confirm
cactus-test-toolingisdevDependencyonly. - Check imported modules actually exist and are correctly referenced.
Workflow
1. Gather: Read all changed files
2. Trace: Follow logic paths through the changes
3. Verify: Check each item on the checklist above
4. Report: Summarize findings as PASS/FAIL with detailsOutput Format
## Doublecheck Report
**Scope**: [files checked]
**Result**: ✅ PASS / ❌ FAIL
### Findings
- [PASS/FAIL] Logic verification: [details]
- [PASS/FAIL] Convention compliance: [details]
- [PASS/FAIL] Test verification: [details]
- [PASS/FAIL] Dependency check: [details]
### Issues Found (if any)
1. [specific issue and location]Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

