round-verification

Verify a CCB execution round and produce a machine-readable round result artifact.

Quality

63%

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_checker/skills/round-verification/SKILL.md

Quality

Content

72%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 body is highly concise and well-structured for a simple decision skill, but it lacks an explicit verification procedure and validation checkpoints, leaving actionability and workflow clarity in the mid-range.

Suggestions

Add a short ordered procedure, e.g. 1) read the verification contract, 2) map worker/checker reports to contract items, 3) confirm command/test evidence, 4) emit the round result.

Insert a validation checkpoint before emitting the result, such as 'verify every contract item has supporting evidence before assigning pass; otherwise downgrade'.

Give one concrete example of matching a report to a contract item and selecting an outcome, to make the decision logic copy-paste ready.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence: it lists only inputs, the output format, and per-outcome decision rules with zero padding or explanation of known concepts, matching the 'lean and efficient; every token earns its place' anchor.	5 / 5
Actionability	The output format and per-outcome rules are concrete decision criteria, but there is no executable procedure for gathering or checking evidence against the verification contract; it fits 'some concrete guidance but incomplete; missing key details' rather than 4 because the verification steps themselves are absent.	3 / 5
Workflow Clarity	The Inputs/Output/Rules sections give an implicit structure but no explicit ordered sequence and no validation checkpoints between gathering reports and emitting a result, matching 'steps listed but validation gaps; checkpoints missing or implicit'; it is above a 2 because the sections do imply a rough flow.	3 / 5
Progressive Disclosure	At under 50 lines with no need for external references, the content is cleanly organized into Inputs, Output, and Rules sections, which per the guideline earns a 5 for simple skills with well-organized sections.	5 / 5
	Total	16 / 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 concise and names a clear, specific niche with two concrete actions, but it omits any explicit trigger guidance ('Use when...'), which caps completeness and limits trigger-term quality.

Suggestions

Add an explicit trigger clause, e.g. 'Use when the orchestrator has returned a round summary and node reports to be verified.'

Broaden trigger-term coverage with natural synonyms users might say, such as 'round verification', 'round result', or 'check round outcome'.

Optionally enumerate the concrete verification actions (e.g. 'check the verification contract against node and checker reports, then emit a round result') to lift specificity toward 4-5.

Dimension	Reasoning	Score
Specificity	The description names the domain ('CCB execution round') and two concrete actions ('Verify' and 'produce a machine-readable round result artifact'), matching the anchor that names a domain plus 1-2 concrete actions without comprehensive coverage; it is not a 4 because only two actions are listed and they are high-level.	3 / 5
Completeness	It clearly states what the skill does ('Verify a CCB execution round and produce a machine-readable round result artifact') but contains no 'Use when...' trigger clause, capping completeness at 3 per the guideline; the 'when' is entirely absent from the description.	3 / 5
Trigger Term Quality	It surfaces relevant domain keywords ('verify', 'round', 'round result artifact') but these are system-specific jargon with no natural synonyms or variations a user would commonly say; it is above a 2 because the terms are at least on-topic rather than generic, but below a 4 due to missing common phrasings.	3 / 5
Distinctiveness Conflict Risk	The 'CCB execution round' niche is specific and unlikely to overlap with unrelated skills, fitting 'mostly distinct; minor overlap risk'; it stops short of 5 because the trigger phrasing is not distinctive enough to fully eliminate overlap with adjacent verification/planning 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_checker/skills/round-verification/SKILL.md
Commit: 01d5b1c

Reviewed: about 20 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.