verify
Skill563 starsChanged 11 days agoMITView on GitHub
Proves a change works before it is called done, and reports the evidence on a ladder from "said" to "ran". Use when you are about to say "done", "fixed", "works" or "ready", when asked to check or test a change, or before opening a pull request.
- Reads credentials
189 other projects use a version of this, 2 of them edited.
Adopted by
Most recently taken up by
- abe238/hotinaitheir own version, first seen Nov 16, 2026
- SmartStudio/baize-bottheir own version, first seen Nov 15, 2026
- YuBan834/vrma-labtheir own version, first seen Nov 15, 2026
- Ju571nK/lodelinetheir own version, first seen Nov 15, 2026
- ericbust/namedroptheir own version, first seen Nov 15, 2026
- automagik-si/genietheir own version, first seen Nov 15, 2026
Used with
Projects with it also use instinct-export, instinct-import and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
TheKREATORSSkillinstinct-export
Export instincts from project/global scope to a file
Also in 3 projects that use this
TheKREATORSSkillinstinct-import
Import instincts from file or URL into project/global scope
Also in 3 projects that use this
AviadPSkillrisk-assess
Assess the risk and blast radius of a proposed code change before implementing it. Evaluates CI impact, framework-wide vs localized scope, rollback path, and identifies blindspots. Use when user says "what's the risk", "is this safe", "assess the impact", "risk assess", "blast radius", or before applying framework-wide or CI-affecting changes. Do NOT use for code quality review (use code-quality) or plan validation (use design-validator).
Also in 3 projects that use this
diego-tobalinaSkillbuild-fix
Fix build and compilation errors systematically. Run when build fails.
Also in 6 projects that use this
AaravChadhaSkillsecure
Security review with a confidence gate - a finding exists only with a concrete exploit scenario and a high/medium/low confidence rating; everything else goes to a worth-hardening list, never inflated. Sweeps five surfaces: auth gates, secrets hygiene, injection and unsafe sinks, unsafe deserialization/crypto/transport, and LLM tool-use trust boundaries. Reports only, never fixes. Use when the user asks for a security review or to check vulnerabilities, secrets, or auth.
Also in 3 projects that use this
ArvorCoSkillspecify
Create feature specification from natural language description. Use when starting a new feature or creating a spec. Triggers on: create spec, specify feature, new feature spec.
Also in 10 projects that use this
- +1 more from TheKREATORS
Other versions189 projects use a version of this.
Word for word · 0
None found.
Edited · 2
- Doist/todoist-cli★ 33257% same
- todoist/todoist-cli★ 33257% same
Wrote their own version · 187
- facebook/react★ 253ksame name
- react/react★ 252ksame name
- garrytan/gstack★ 142ksame name
- oven-sh/bun★ 97ksame name
- anthropics/financial-services-plugins★ 41ksame name
- anthropics/financial-services★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- anthropics/claude-quickstarts★ 19ksame name
- NVIDIA-NeMo/NeMo★ 19ksame name
177 more not listed
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 repository9 other files it gives its agents.
- AGENTS.mdAGENTS.md
- docs/agents.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- build-featureSkill
- fix-bugSkill
- learnSkill
- refactorSkill
- review-changesSkill
- write-testsSkill
The file
Files
Verify a change
1. Run the checks
npm run verifyIt runs every check CI runs (about ten seconds) and records the pass. Fix every failure; never weaken a check to pass it. Done when it prints Verified., or says only docs changed and there is nothing to check.
2. Prove the change itself
The checks prove nothing broke. Now prove the change does what was asked, with the proof its kind needs:
| Change | Proof |
| Tool behaviour (input → API call → output) | A test in src/tools/<tool>.test.ts that fails without the change. Run it with the change undone once and see it fail. |
| How the SDK or the API is called | A *.sdk.test.ts that goes through the real TodoistApi with a customFetch (see src/tools/add-projects.sdk.test.ts). |
Tool descriptions or instructions | npm run eval -- --label before and --label after; diff tmp/eval/*.json. It calls paid models: say so before running. |
| Schema shape | npm run verify covers lint:schemas, output-schema-nullability.test.ts and tool-annotations.test.ts. Add a test for new rules. |
| Token cost of the tool surface | src/token-footprint.test.ts (in verify). If you raise DEFAULT_TOKEN_BUDGET, say so in the PR. |
| A real Todoist answer | npm run tool -- <tool> '<json>', only on a test account. Check npm run tool -- user-info '{}' first. Ask before writes. |
MCP Apps widget (src/mcp-apps) | npm run dev, open the inspector, call the tool, look at the widget, screenshot it, check the console. It uses .env's token: test account only, ask before writes. |
Agent tooling (.agents/scripts) | Its tests in throwaway repos, plus one real run of the hook or command. |
| Docs only | Every path and command named exists (ls, npm run). |
Check the proof can fail: undo the change and see the test fail, or run the scenario that used to break. Done when you have seen it fail and then pass. A refactor is the exception: its proof is the pinned tests passing before and after (see refactor).
3. Report the evidence
Rate every claim on this ladder:
- said: stated without looking.
- cited: the line that shows it (
path:line). - traced: followed the code path through each call.
- ran: a test or command executed the code and showed the result.
- seen: observed in the running server or widget.
Claims about behaviour ("fixed", "works", "safe", "no regressions") need ran or higher. A fact the code shows needs cited. Anything lower goes under Not verified, with why.
For a change to code others rely on (shared helpers in src/utils/, src/tool-helpers.ts, schemas in output-schemas.ts, the public API in src/index.ts), name the one fact that makes it safe, and how you proved it.
Report format:
What changed: <one line>
Verified:
- <claim> — ran: <command or test>, <what it showed>
Not verified:
- <claim> — <why>
Safe because: <the one fact>, <how you proved it> (only for shared code)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.

