orchestration-bundle-candidate

Select one route and return one adaptive one-to-four-workgroup bundle candidate as reply-only evidence.

Quality

51%

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_orchestrator/skills/orchestration-bundle-candidate/SKILL.md

Quality

Content

63%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 an unusually precise, jargon-dense specification with exact field-level constraints and explicit validation/failure gates, but it buries a fully specified schema without a single example and consolidates everything into one long file. Constraint repetition across sections inflates token cost without adding information.

Suggestions

Include one complete example JSON bundle candidate (covering both a one-node and a multi-node case) so the fully specified schema is copy-paste executable rather than derivable.

Move the field-level schema specification (root/selection/integration/policy field lists and literal values) into a reference file referenced from the body, keeping SKILL.md as the decision-oriented overview.

De-duplicate the selection rules: the capacity-not-a-target, dependency-evidence, and node-count rules are each restated in both the prose and bullet sections; state each constraint once.

Dimension	Reasoning	Score
Conciseness	The body is dense and free of explanations of concepts Claude already knows, but constraint rules are restated multiple times across sections (capacity-is-not-a-target, dependency-stability, and node-count rules each appear twice or more), so it could be meaningfully tightened.	3 / 5
Actionability	Guidance is highly concrete — exact field names, literal policy values, ID format rules, and character limits — but it never shows an example JSON bundle despite fully specifying one, leaving a real executable gap.	4 / 5
Workflow Clarity	The reply contract is numbered and sequenced, verification gates are explicit (refs must contain direct argv commands), and there is a clear failure path (return structural replan_required evidence instead of emitting a bundle); minor gaps remain because no validate-fix-retry loop is articulated.	4 / 5
Progressive Disclosure	The skill is a single 130+ line file with clear section headers but no external reference files at all; the schema field specification is exactly the kind of detail that belongs in a one-level-deep reference file, so structure is only partly appropriate.	3 / 5
	Total	14 / 20 Passed

Description

38%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 names a concrete action but is written entirely in internal orchestration jargon with no natural trigger terms and no 'when to use' guidance. It would rarely be selected by a user's natural phrasing and reads as a system-internal label rather than a discovery description.

Suggestions

Add an explicit 'Use when...' clause stating when this skill applies (e.g., 'Use when the orchestrator controller requests a route decision and workgroup bundle candidate for a decomposed task').

Replace or gloss internal jargon ('workgroup bundle candidate', 'reply-only evidence') with terms a caller would naturally use, such as 'task decomposition', 'route decision', or 'agent workgroup plan'.

Briefly enumerate the concrete outputs (route decision, orchestration notes, JSON bundle candidate) so the 'what' is comprehensive rather than a single compressed clause.

Dimension	Reasoning	Score
Specificity	The description states concrete actions ('Select one route and return one adaptive one-to-four-workgroup bundle candidate as reply-only evidence') but covers only this single action pair and wraps it in dense internal jargon, so it is neither fully vague nor comprehensively specific.	3 / 5
Completeness	A 'what' is present (select one route, return a bundle candidate) but there is no 'when' or 'Use when...' trigger clause of any kind, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	There are no natural keywords a user would say; terms like 'workgroup bundle candidate', 'route', and 'reply-only evidence' are pure orchestration-system jargon, matching the 'only technical jargon' anchor.	1 / 5
Distinctiveness Conflict Risk	The description is highly niche and internal-specific, so overlap with other skills is minimal; it falls short of a 5 because its distinctiveness comes from obscure jargon rather than clear, natural trigger phrases.	4 / 5
	Total	11 / 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_orchestrator/skills/orchestration-bundle-candidate/SKILL.md
Commit: 18bf0af

Reviewed: 7 days 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.