agentleFS
Sign inStart free
SnoozleStudioSnoozleStudio/opencode-wp-settings/skills/verify/SKILL.md

verify

Skill4 starsChanged 3 days agoMITView on GitHub

Adversarial verification that code, logic, or a completed task is CORRECT. Use for "double check this logic", "prove it", "is this bug really fixed". Three-agent pattern — finder finds issues, adversary tries to disprove them, referee judges. For high-stakes correctness. Not for standards/spec review (use review) or attack-surface security (use wp-security-audit).

189 other projects use a version of this.

Adopted by

Most recently taken up by

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.
  • TheKREATORSSkill

    instinct-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

  • AviadPSkill

    risk-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-tobalinaSkill

    build-fix

    Fix build and compilation errors systematically. Run when build fails.

    Also in 6 projects that use this

  • AaravChadhaSkill

    secure

    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

  • ArvorCoSkill

    specify

    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

The file

We split this skill into the rules it gives an agent

2 rules. 0 are common, 2 are distinctive, and 0 are very specific to this project.

  • 0

    Common

    Most of the 167 edited versions we read keep these.

  • 2

    Distinctive

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Never verify by rerunning the same check that failed — change the angle

    line 32
  2. Distinctive:

    Never fake measurements: if verification requires a tool you can't run, say so

    line 33

“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.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Adversarial Verification

Prove the work is right — not by re-reading it fondly, but by attacking it.

Pattern

  1. Finder (subagent): analyze the target (diff, function, flow) for correctness bugs, edge cases, incoherences. Neutral prompt — "analyze and report all findings"
  2. Adversary (subagent): take each finding and try to disprove it. A finding that survives the adversary is real; one that doesn't is dropped. This kills false positives without argument
  3. Referee (you): judge the survivors. Classify each as confirmed/plausible with severity. Confirmed blockers stop the work; plausible findings get verified by reading code or running the path

What to verify

  • Logic correctness (off-by-one, empty states, error paths)
  • WordPress contract: escaping chain on every output, nonce + capability pairing, $wpdb->prepare, hook timing
  • Data flow: input → sanitize → validate → store → escape → output, end to end
  • Cleanup: every initialized lib can be torn down (Lenis destroy, context revert, Tempus unsubscribe, Three dispose)

Rules

  • Never verify by rerunning the same check that failed — change the angle
  • Never fake measurements: if verification requires a tool you can't run, say so
  • Two agents agreeing on a false positive is not a mandate — the referee decides with evidence

Output

Findings table (status CONFIRMED/PLAUSIBLE, severity, file:line, failure scenario), verdict per item, and a final go/no-go.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free