verification-loop
A comprehensive verification system for Claude Code sessions.
40
38%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./.claude/skills/verification-loop/SKILL.mdQuality
Discovery
0%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 description is critically underspecified. It fails to explain what specific actions the skill performs, what 'verification' means in this context, and when Claude should select it. The buzzword 'comprehensive' adds no informational value, and the lack of concrete triggers or use cases makes it nearly impossible to distinguish from other skills.
Suggestions
Replace 'comprehensive verification system' with specific concrete actions, e.g., 'Validates tool outputs, checks code execution results, and confirms task completion in Claude Code sessions.'
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user asks to verify, validate, or double-check results from a Claude Code session.'
Clarify what 'verification' entails to distinguish this skill from testing, linting, or code review skills—specify the exact scope and unique niche.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses vague, abstract language ('comprehensive verification system') without naming any concrete actions. It does not specify what is being verified or how. | 1 / 3 |
Completeness | The description weakly addresses 'what' (a verification system) but provides no 'when' clause or explicit trigger guidance. Both dimensions are very weak. | 1 / 3 |
Trigger Term Quality | The only potentially relevant terms are 'verification' and 'Claude Code sessions,' which are technical jargon unlikely to match natural user queries. No common user-facing trigger terms are present. | 1 / 3 |
Distinctiveness Conflict Risk | The description is extremely generic—'comprehensive verification system' could overlap with testing, linting, code review, validation, or many other skills. There is nothing to distinguish it clearly. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a solid, actionable verification workflow skill with clear sequencing, explicit validation gates, and concrete commands throughout. Its main weakness is moderate verbosity—some sections (Continuous Mode, Integration with Hooks, When to Use) add little value and could be trimmed. The lack of bundle files means all content is inline, which is acceptable given the skill's length but could benefit from splitting.
Suggestions
Remove or significantly trim the 'When to Use', 'Continuous Mode', and 'Integration with Hooks' sections—they add little actionable value and consume tokens.
Consider extracting the security scan grep patterns and the output format template into separate referenced files if the skill grows further.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | Generally efficient but includes some unnecessary sections like 'Continuous Mode' with vague advice ('set a mental checkpoint') and the 'Integration with Hooks' section which adds little value. The 'When to Use' section explains obvious triggers Claude could infer. | 2 / 3 |
Actionability | Every phase includes concrete, copy-paste-ready bash commands with specific flags and output piping. The output format template is fully specified, and the pre-push gate has explicit, actionable rules. | 3 / 3 |
Workflow Clarity | Clear 6-phase sequence with explicit stop/fix gates (Phase 1: 'STOP and fix before continuing'), validation checkpoints at each phase, a structured output report, and a mandatory pre-push gate with a fix-then-rerun feedback loop. | 3 / 3 |
Progressive Disclosure | Content is well-structured with clear headers and phases, but everything is inline in a single file. The security scan patterns, output format template, and pre-push rules could be split into referenced files for a cleaner overview. However, no bundle files exist to reference. | 2 / 3 |
Total | 10 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- devrev/meerkat
- Commit
b09913f
- Reviewed
Table of Contents
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.