orchestrator-capacity

Historical reference for script-owned loop capacity requests. Do not use from provider sessions.

Quality

45%

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/adapters/ccb/skills/orchestrator-capacity/SKILL.md

Quality

Content

61%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 a lean, well-organized boundary reference that assumes competence and avoids padding. Its weakness is actionability and workflow clarity: it gives directives and a reply template but no executable steps or validation checkpoints for the capacity/routing operations it governs.

Suggestions

Add a concrete reply example or template showing the exact semantic-evidence shape, so the guidance is copy-paste ready rather than descriptive.

Include a validation step (e.g., 'verify requested profiles are non-empty before recommending capacity') to raise workflow clarity above the destructive/batch cap of 3.

Clarify which fields of the task packet and verification refs must be quoted, turning the reply-shape bullets into an explicit checklist.

Dimension	Reasoning	Score
Conciseness	The body is short and assumes reader competence, listing boundaries and reply shape without explaining concepts Claude already knows; only minor phrases ('is now runner-owned') could be tightened.	4 / 5
Actionability	Guidance is concrete in intent ('Do not run CCB commands', 'reply with semantic evidence only') but consists of directives and bullet labels rather than executable commands or copy-paste examples, leaving it incomplete as actionable instruction.	3 / 5
Workflow Clarity	The reply shape lists what to include (profiles, counts, refs, blockers, recommendation) giving a rough sequence, but there are no validation checkpoints or feedback loops; per the rubric, a process handling capacity/routing without validation caps at 3.	3 / 5
Progressive Disclosure	Content is well-sectioned (Provider Boundary, Reply Shape) with no bundle files to reference and no nested pointers; for a short single-purpose reference this is appropriately organized, just shy of an ideal overview-with-references structure.	4 / 5
	Total	14 / 20 Passed

Description

28%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 terse and establishes a clear anti-trigger boundary, but it reads as an internal deprecation notice rather than an actionable skill description. It lacks concrete actions, natural trigger terms, and a positive use-when clause.

Suggestions

State the concrete capability (e.g., 'Records recommended loop capacity for ...') instead of the generic word 'reference'.

Add a positive 'Use when ...' clause naming the natural trigger terms a user would say, rather than only the 'Do not use from provider sessions' exclusion.

Replace internal jargon ('script-owned', 'provider sessions') with user-facing vocabulary or add synonyms so it is discoverable.

Dimension	Reasoning	Score
Specificity	The phrase 'Historical reference for script-owned loop capacity requests' names the domain (loop capacity) but the only 'action' is 'reference,' with no concrete actions enumerated; it falls between anchors 1 and 3.	2 / 5
Completeness	It states a vague 'what' (a historical reference) and an anti-trigger ('Do not use from provider sessions') but never gives a positive 'when to use' clause, capping completeness well below a clear what+when pair.	2 / 5
Trigger Term Quality	'loop capacity requests' and 'provider sessions' are internal jargon rather than natural user phrases; only a couple generic terms appear and the natural vocabulary users would say is missing.	2 / 5
Distinctiveness Conflict Risk	The niche (script-owned loop capacity) is fairly specific and the explicit 'Do not use from provider sessions' boundary reduces misfire risk, but it is so terse it could still overlap with general orchestration/capacity skills.	3 / 5
	Total	9 / 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/adapters/ccb/skills/orchestrator-capacity/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.