round-verification

Verify integrated round evidence and return a machine-readable round result for script import.

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_round_reviewer/skills/round-verification/SKILL.md

Quality

Content

78%Weight 40%Scale 1-5

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

The content is tightly written, well-structured, and actionable with explicit validation checkpoints and boundaries. It would benefit from defining a couple of domain-specific rejection terms inline and trimming the slight repetition around the output-format rules.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, but the output-format enforcement paragraph partially repeats step 3's instruction, giving minor over-explanation.	4 / 5
Actionability	Concrete, specific guidance is given (exact result line format, first-line rules, explicit rejection conditions), though a few domain terms like "integration drift" and "rollback drift" are not defined inline.	4 / 5
Workflow Clarity	A clear three-step sequence includes an explicit validation/rejection checkpoint and an insufficient-evidence recovery path ("round result: blocked"), with only minor gaps.	4 / 5
Progressive Disclosure	This single-purpose skill is under 50 lines with no bundle files and is cleanly sectioned into Workflow and Boundaries, meeting the simple-skill exception for a top score.	5 / 5
	Total	17 / 20 Passed

Description

53%Weight 40%Scale 1-5

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 concrete about what the skill does but lacks an explicit when-to-use trigger and relies on domain jargon over natural user phrasing. It is reasonably distinct within its pipeline niche.

Suggestions

Add a "Use when ..." clause naming the natural trigger situation (e.g., after a round's review/integration/promotion evidence is assembled).

Soften internal jargon with one or two natural terms a user might actually say when invoking this skill.

Optionally enumerate the concrete verification actions (check node review, integration, promotion, root checks) to lift specificity above two actions.

Dimension	Reasoning	Score
Specificity	The description names the domain and two concrete actions ("Verify integrated round evidence" and "return a machine-readable round result"), but coverage is narrow rather than comprehensive.	3 / 5
Completeness	The "what" is clear (verify round evidence, return a machine-readable result) but there is no "Use when..." clause or equivalent trigger, capping completeness at 3 per the rubric guidance.	3 / 5
Trigger Term Quality	It includes several domain-relevant keywords ("round evidence", "round result", "script import") but these are internal jargon rather than natural phrases a user would say, and common variations are absent.	3 / 5
Distinctiveness Conflict Risk	The round-verification niche is fairly distinct with specific pipeline terminology, carrying only minor overlap risk with closely related sibling review skills.	4 / 5
	Total	13 / 20 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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: SeemSeam/claude_codex_bridge
Path: docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_round_reviewer/skills/round-verification/SKILL.md
Commit: 01d5b1c

Reviewed: about 21 hours 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.