verify
Skill67 starsChanged 4 months agoMITView on GitHub
Verify outputs after pipeline steps, implementations, or any multi-step work. Catches missing data, stale references, broken assumptions. Use after completing significant work, before declaring done.
188 other projects use a version of this.
Adopted by
Most recently taken up by
- Doist/todoist-aitheir own version, first seen Nov 9, 2026
- udecode/better-convextheir own version, first seen Nov 9, 2026
- pytorch/heliontheir own version, first seen Nov 8, 2026
- amir20/dozzletheir own version, first seen Nov 8, 2026
- Doist/todoist-clitheir own version, first seen Nov 8, 2026
- codewithmukesh/dotnet-claude-kittheir own version, first seen Nov 8, 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
- TheKREATORSSkill
instinct-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 versions188 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 188
- react/react★ 252ksame name
- facebook/react★ 252ksame name
- garrytan/gstack★ 141ksame name
- oven-sh/bun★ 97ksame name
- anthropics/financial-services★ 41ksame name
- anthropics/financial-services-plugins★ 41ksame name
- Yeachan-Heo/oh-my-claude-sisyphus★ 41ksame name
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- anthropics/claude-quickstarts★ 19ksame name
- NVIDIA-NeMo/Speech★ 19ksame name
178 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 repository24 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- autoresearchSkill
- brainstormSkill
- bug-huntSkill
- check-resolvableSkill
- compSkill
- debugSkill
- dialectic-reviewSkill
- distillSkill
- finalizeSkill
- implementSkill
- learnSkill
- plan-taskSkill
- premortemSkill
- red-teamSkill
- researchSkill
- retroSkill
- reviewSkill
- rsbSkill
- sessionsSkill
- shipSkill
- socratesSkill
- tradeoffSkill
- wrapupSkill
The file
We split this skill into the rules it gives an agent
10 rules. 0 are common, 8 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 167 edited versions we read keep these.
8
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 11
Run after any significant output to catch what was missed.
- Distinctive: line 17
If no arguments, verify the most recent significant output or pipeline step.
- Very specific: line 34
Read the relevant files and run checks appropriate to the type.
- Distinctive: line 55
If everything passes, say so concisely.
- Very specific: line 59
If Step 3 reports FAILED items, do not jump to fixing.
- Distinctive: line 62
If you catch yourself or a subagent using any of these phrases, STOP and re-verify:
- Distinctive: line 68
If a verification failure has been "fixed" 3 times and still fails, STOP.
- Distinctive: line 72
Don't just verify what was done.
- Distinctive: line 73
When verifying data pipelines, always check the enrichment chain: raw → enriched → categorized → indexed.
- Distinctive: line 75
After writing to MEMORY.md or project docs, verify the information is actually findable by future agent sessions (discoverability check).
“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
Run after any significant output to catch what was missed. The goal is to prevent the class of error where work appears complete but isn't — unfetched data, stale counts, broken assumptions, missing files.
Input
Target to verify: $ARGUMENTS
If no arguments, verify the most recent significant output or pipeline step.
Process
Step 1: Identify What to Verify
Determine the verification type from context:
| Type | Trigger | What to Check |
| Data pipeline | After running a pipeline (refresh, ETL, etc.) | Row counts, coverage rates, missing fields, stale references |
| Implementation | After implementing from a plan | All plan items addressed, tests pass, no regressions |
| Analysis | After producing analysis/reports | Claims supported by data, no unfetched sources, numbers consistent |
| File output | After generating files | Files exist, non-empty, correct format, no orphan references |
Step 2: Run Checks
Read the relevant files and run checks appropriate to the type. See ~/.claude/skills/verify/check-types.md for the four composable check categories (data, completeness, consistency, assumption). A single verification usually draws from multiple categories — e.g., a data pipeline verification runs data + completeness + consistency.
Step 3: Report
Format findings as:
VERIFICATION — [target]
PASSED:
- [check]: [result]
FAILED:
- [check]: [what's wrong] → [suggested fix]
WARNINGS:
- [check]: [not broken but suspicious]
COVERAGE: [X/Y checks passed]If everything passes, say so concisely. Don't pad the report.
Step 4: When Verification Fails — Debug Protocol
If Step 3 reports FAILED items, do not jump to fixing. See ~/.claude/skills/verify/debug-protocol.md for the full 4-phase protocol.
Red Flag Language (from Superpowers)
If you catch yourself or a subagent using any of these phrases, STOP and re-verify:
- "Done!", "should work", "probably fine", "seems to", "I believe this handles"
- "Great!", "Perfect!" (sycophantic completion signals) These indicate a completion claim without fresh evidence. Run the actual checks.
Three-Fix Escalation Rule (from Superpowers)
If a verification failure has been "fixed" 3 times and still fails, STOP. Don't try a fourth fix. The architecture is probably wrong. Escalate to the user: "This has failed 3 fixes. The approach itself may need rethinking."
Gotchas
- The most dangerous failures are silent ones — things that LOOK complete but aren't. Prioritize checking those.
- Don't just verify what was done. Verify what SHOULD have been done but might have been skipped.
- When verifying data pipelines, always check the enrichment chain: raw → enriched → categorized → indexed. A break at any stage propagates silently.
- Stale counts in COMP files are the most common consistency failure after batch operations.
- After writing to MEMORY.md or project docs, verify the information is actually findable by future agent sessions (discoverability check).
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.