CtrlK
BlogDocsLog inGet started
Tessl Logo

verification-loop

A comprehensive verification system for Claude Code sessions.

38

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

SKILL.md
Quality
Evals
Security

Quality

Content

72%

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

The content is highly actionable with concrete commands and a clear phased structure, losing points only on minor verbosity and uneven validation checkpoints across the later phases.

Suggestions

Remove the duplicated description line after the frontmatter and tighten prose like the hooks comparison paragraph to improve token efficiency.

Add explicit stop/fix checkpoints to the lint, security, and diff phases so every phase has a clear validation gate, lifting workflow clarity.

Define explicit pass/fail thresholds (e.g. the implied 80% coverage) inline per phase so the verdict criteria are unambiguous.

DimensionReasoningScore

Conciseness

The body is mostly lean and command-focused, but it repeats the frontmatter description verbatim and includes some soft prose ('This skill complements PostToolUse hooks...') that could be trimmed, so it is efficient but not maximally tight.

2 / 3

Actionability

It provides concrete, copy-paste-ready commands throughout (e.g. 'npm run build 2>&1 | tail -20', 'npx tsc --noEmit 2>&1 | head -30', 'git diff --stat') matching the fully-executable score-3 anchor.

3 / 3

Workflow Clarity

The six phases give a clear sequence with one explicit checkpoint ('If build fails, STOP and fix before continuing') and a final report, but later phases (lint, security, diff) lack explicit validation or feedback-loop checkpoints, leaving gaps as the score-2 anchor describes.

2 / 3

Progressive Disclosure

No bundle files exist and the skill is a single self-contained document organized into clear, well-labeled sections with no nested references, so organization is appropriate and navigation is easy per the simple-skill scoring note.

3 / 3

Total

10

/

12

Passed

Description

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.

The description is a single vague sentence with no concrete actions, no user-facing trigger terms, and no explicit usage guidance, so it scores at the floor on every dimension.

Suggestions

Replace 'comprehensive verification system' with concrete actions, e.g. 'Runs build, type-check, lint, test, security, and diff reviews for a change'.

Add an explicit trigger clause: 'Use when finishing a feature, before opening a PR, or when you need quality gates to pass'.

Include natural user keywords like 'verification', 'quality gates', 'pre-PR check', and 'run checks' so the skill is distinguishable and discoverable.

DimensionReasoningScore

Specificity

The description 'A comprehensive verification system for Claude Code sessions' names no concrete actions, relying on the abstract phrase 'verification system', which matches the vague-language anchor rather than naming specific capabilities.

1 / 3

Completeness

The 'what' is only weakly stated ('verification system') and the 'when' is entirely absent with no explicit trigger guidance, so both halves are weak as the score-1 anchor describes.

1 / 3

Trigger Term Quality

There are no natural keywords a user would say when needing this skill and no 'Use when...' trigger clause; 'verification system' is generic jargon rather than user-facing trigger terms.

1 / 3

Distinctiveness Conflict Risk

'A comprehensive verification system for Claude Code sessions' is very generic and would overlap with many quality-gate or review skills, matching the high-conflict score-1 anchor.

1 / 3

Total

4

/

12

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
affaan-m/everything-claude-code
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.