verify
Skill2 starsChanged 4 months agoMITView on GitHub
Lightweight self-check — runs each touched module's lint/build commands as configured in its profile YAML. Not a full review; just "did I break something obvious?
189 other projects use a version of this.
Adopted by
Most recently taken up by
- 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
- todoist/todoist-clitheir 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 · 0
None found.
Wrote their own version · 189
- 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
179 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.
The file
We split this skill into the rules it gives an agent
4 rules. 0 are common, 0 are distinctive, and 4 are very specific to this project.
0
Common
Most of the 167 edited versions we read keep these.
0
Distinctive
This author's own choices. Worth a look.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 29
Run the lint: command (if present).
- Very specific: line 30
Run the build: command — only if quick_build: true is set in the profile (otherwise skipped, since builds can be slow).
- Very specific: line 46
If a changed file matches no profile, /verify reports "unknown module" for that file (so you don't silently skip it).
- Very specific: line 74
If you'd like the team to fix the lint errors instead of you, run /start "fix lint errors in <module>: <paste of failures>" — the planner …
“Common” is measured: kept by at least 6 in 10 of the 167 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
/verify — Quick self-check
A pre-flight: lint + (optionally) build the modules whose files you've changed, before handing them to the pipeline. Catches obvious syntax / typecheck / lint errors in seconds rather than minutes-into-review.
This is not the code review. The actual review happens inside the
pipeline (review-correctness + review-convention + review-quality +
tester). /verify is just the developer's local sanity check.
Usage
/verify # auto-detect modules from `git diff --name-only`
/verify <module> # check one specific module
/verify <m1> <m2> # check several at onceWhat it does
For each module to check:
- Read
.claude/profiles/<module>.yaml. - Run the
lint:command (if present). - Run the
build:command — only ifquick_build: trueis set in the profile (otherwise skipped, since builds can be slow). - Capture stdout / stderr / exit code per module.
- Report PASS / FAIL per module with a per-finding breakdown when FAIL.
Module detection
git diff --name-only is mapped against each profile's paths patterns:
# .claude/profiles/<module>.yaml
paths:
- "apps/<module>/**"
- "libs/<module>/**"If a changed file matches no profile, /verify reports "unknown module"
for that file (so you don't silently skip it). If a file matches multiple
profiles, the more specific path pattern wins (longest path-prefix match).
Output
VERIFY REPORT
=============
Time: 2026-04-27T14:32:00Z
Detected modules: shared, worker, frontend
[PASS] shared — lint OK (3.2s)
[PASS] worker — lint OK (5.1s)
[FAIL] frontend — lint: 3 errors, 2 warnings (4.7s)
<file>:<line>:<col> — <rule> — <message>
<file>:<line>:<col> — <rule> — <message>
<file>:<line>:<col> — <rule> — <message>
Total: 2 PASS, 1 FAIL — 12.9sOn FAIL
/verify lists the linter's errors verbatim. It does not offer to
fix them — that's the developer's job (or the developer agent's, when the
pipeline runs). /verify is a check, not a fixer.
If you'd like the team to fix the lint errors instead of you, run
/start "fix lint errors in <module>: <paste of failures>" — the
planner detects the bug shape from the phrasing and routes through the
pipeline.
Common scenarios
| Scenario | What to expect |
/verify with no changes | "No changed files detected. Nothing to verify." |
/verify and one of the changed files matches no profile | Reports the file with [?] no profile matched — you should add or extend a profile's paths |
Profile has lint: but command isn't installed | [FAIL] <module> with stderr showing the not-found error — install the tool |
quick_build: true and build is slow | Verify takes longer; if too slow, set quick_build: false |
What it does NOT do
- ❌ Run the test suite (that's the tester agent's job in the pipeline)
- ❌ Spawn any agent
- ❌ Touch
.state/ - ❌ Modify any file
- ❌ Auto-fix lint findings
Notes
We use /verify as a pre-team.sh start sanity check after manual
edits. If your manual change has an obvious lint or syntax error,
catching it here saves the developer agent from wasting a retry cycle on
something you already know is broken.
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.

