verify

Enforces fresh verification evidence before any completion or success claims. Use when about to say "done", "fixed", "tests pass", "build succeeds", or any synonym; before committing, creating PRs, or moving to the next task; before expressing satisfaction or positive statements about work state; and after agent delegation to independently verify results. Prevents unverified claims by requiring command execution, output inspection, and exit code confirmation.

Quality

85%

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

70%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-structured behavioral skill that clearly communicates when and how to verify before claiming completion. Its main strengths are the clear 5-step workflow, comprehensive evidence table, and anti-pattern recognition. Its weaknesses are some redundancy across sections and the lack of concrete executable examples (all examples are pattern-level rather than copy-paste ready commands).

Suggestions

Consolidate the 'Why Partial Verification Fails' table into the 'What Counts as Evidence' table to reduce redundancy and save tokens.

Replace pseudocode patterns like '[Run test command] [See: 34/34 pass]' with at least one concrete executable example (e.g., `pytest --tb=short` with sample output) to improve actionability.

Dimension	Reasoning	Score
Conciseness	The skill is reasonably efficient but has some redundancy — the 'Why Partial Verification Fails' table largely repeats information from the 'What Counts as Evidence' table and 'Recognizing Unverified Claims' section. The 'Why This Matters' section with failure memories adds motivational context that Claude doesn't need. Some tightening is possible.	2 / 3
Actionability	The skill provides clear patterns (OK vs BAD) and a structured verification process, but lacks executable commands — all code examples are pseudocode-level patterns like '[Run test command] [See: 34/34 pass]' rather than concrete commands. The guidance is specific in structure but abstract in execution details.	2 / 3
Workflow Clarity	The 5-step verification workflow (Identify → Run → Read → Verify → Claim) is clearly sequenced with explicit validation checkpoints and feedback loops (if no: state actual status; if yes: state claim with evidence). The regression test pattern includes a full red-green cycle. The workflow is well-suited to this behavioral skill.	3 / 3
Progressive Disclosure	For a standalone skill with no bundle files, the content is well-organized with clear sections progressing from principle → steps → evidence tables → anti-patterns → examples → when to apply. The length is appropriate for inline content without needing external references.	3 / 3
	Total	10 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is an excellent skill description that clearly defines a specific behavioral guardrail with comprehensive trigger conditions. It uses third person voice, provides concrete actions, and includes an explicit 'Use when' clause with multiple well-articulated scenarios. The description is both concise and thorough, making it easy for Claude to know exactly when to apply this skill.

Dimension	Reasoning	Score
Specificity	Lists multiple specific concrete actions: 'command execution, output inspection, and exit code confirmation.' Also specifies concrete scenarios like committing, creating PRs, agent delegation, and expressing satisfaction about work state.	3 / 3
Completeness	Clearly answers both 'what' (enforces fresh verification evidence, requires command execution/output inspection/exit code confirmation) and 'when' (explicit 'Use when' clause with four detailed trigger scenarios covering completion claims, commits/PRs, satisfaction expressions, and agent delegation).	3 / 3
Trigger Term Quality	Excellent coverage of natural trigger terms users/Claude would encounter: 'done', 'fixed', 'tests pass', 'build succeeds', 'committing', 'creating PRs', 'moving to the next task', 'agent delegation'. These are terms that naturally arise in development workflows.	3 / 3
Distinctiveness Conflict Risk	This skill occupies a very clear niche — verification discipline before claiming success. It's unlikely to conflict with other skills since it's about a meta-behavior (verification enforcement) rather than a domain-specific task. The triggers are distinct and specific to completion/success claim scenarios.	3 / 3
	Total	12 / 12 Passed

Validation

100%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 11 / 11 Passed

Validation for skill structure

No warnings or errors.

Repository: shousper/claude-kit
Commit: 08bc600

Reviewed: 14 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.