CtrlK
BlogDocsLog inGet started
Tessl Logo

node-check

Verify one CCB worker node and reject hidden fallback, degradation, scope shrinkage, or missing evidence.

67

Quality

80%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./docs/plantree/plans/agentic-loop-workflow/drafts/agentroles.ccb_checker/skills/node-check/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The content is a tight, well-structured review/gatekeeping workflow with explicit validation checkpoints, concrete verdict formatting, and clear negative boundaries. It respects token budget and assumes Claude's competence throughout.

DimensionReasoningScore

Conciseness

The body is lean and directive with no concept explanations Claude already knows; every line (e.g. "Return a parser-stable machine verdict as the first non-empty line") earns its place.

3 / 3

Actionability

It gives concrete, specific guidance such as the exact verdict strings ("status: pass", "status: rework_required", "status: blocked", "status: non_converged") and specific forbidden commands ("ccb", "ccb_test"); per the scoring notes, absence of code in an instruction-only skill is not penalized when guidance is actionable.

3 / 3

Workflow Clarity

The seven-step sequence includes explicit validation checkpoints ("Missing or mismatched visible identity is blocked", "otherwise report the missing proof") and branching verdicts, matching the anchor for a clear sequence with explicit validation steps.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no external references needed and is well-organized into Workflow and Boundaries sections; per the scoring notes this qualifies for a 3 with just well-organized sections.

3 / 3

Total

12

/

12

Passed

Description

60%

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 states a concrete action and concrete output verdicts but omits any explicit use-trigger and leans on internal jargon rather than natural user terms. It is specific in capability yet incomplete in when-to-use guidance.

Suggestions

Add an explicit 'Use when...' trigger clause, e.g. 'Use when a Worker supplies a coder node review packet for verification.'

Soften internal jargon ('coder node', 'execution contract', 'non-converged') with natural terms a user would actually say, such as 'code review', 'acceptance check', or 'not converged'.

Keep the four outcome states but pair them with user-facing phrasing so the trigger context is clear.

DimensionReasoningScore

Specificity

"Verify one coder node against the assigned execution contract" names a concrete action and "return pass, rework, blocked, or non-converged" lists multiple specific concrete outcomes, matching the anchor for listing multiple specific concrete actions.

3 / 3

Completeness

It clearly states what the skill does (verify a node, return a verdict) but lacks any "Use when..." trigger guidance, so per the judging guidelines completeness is capped at 2 with the "when" missing.

2 / 3

Trigger Term Quality

Terms like "coder node", "execution contract", and "non-converged" are internal domain jargon rather than natural phrases a user would say; it has some relevant keywords but is missing common natural variations.

2 / 3

Distinctiveness Conflict Risk

"coder node", "execution contract", and "non-converged" carve out a fairly specific review niche but the abstract terminology could still overlap with general verification/review skills, matching the "somewhat specific but could overlap" anchor.

2 / 3

Total

9

/

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
SeemSeam/claude_codex_bridge
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.