ask

Send a request to a CCB agent with `ask`.

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./inherit_skills/claude_skills/ask/SKILL.md

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 lean, highly actionable, and well-sequenced with explicit recovery guidance and a clear decision checklist. It is a strong, self-contained skill body with no significant gaps.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence, with no padding explaining basic concepts; every line earns its place with CCB-specific protocol detail.	3 / 3
Actionability	Provides copy-paste-ready heredoc command patterns, an exact receipt shape, and concrete flag-selection rules rather than abstract direction.	3 / 3
Workflow Clarity	The Decision Card is a sequenced three-step checklist, and the Guardrails section supplies explicit error-recovery feedback loops (e.g. retry with plain ask on chain-rejection, cancel-and-resubmit on rejected corrections).	3 / 3
Progressive Disclosure	No bundle files exist and none are needed; the single file is organized into clear labeled sections (Decision Card, Guardrails, Receipt Contract, command examples) appropriate for its scope.	3 / 3
	Total	12 / 12 Passed

Description

57%

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 pinpoints a distinct niche but is missing explicit trigger guidance and only names a single action. Adding a "Use when..." clause and broader trigger terms would raise the score.

Suggestions

Add a "Use when..." clause naming delegation scenarios, e.g. "Use when the user asks to delegate a task to a CCB agent or hand off subwork."

Broaden trigger terms to include natural variations like "delegate", "handoff", or "subtask collaboration" alongside "ask".

Mention a second concrete action (e.g. propagating continuations, artifact-preserving replies) to lift specificity.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Send a request") and domain ("CCB agent") but lists only a single action rather than the multiple specific actions the skill actually supports.	2 / 3
Completeness	Clearly states what the skill does but provides no "Use when..." trigger guidance, which caps completeness at 2 per the rubric.	2 / 3
Trigger Term Quality	Includes relevant terms ("ask", "request", "CCB agent") but "CCB" is jargon and natural variations users might say ("delegate", "handoff", "collaboration") are absent.	2 / 3
Distinctiveness Conflict Risk	"CCB agent with ask" carves out a clear, tool-specific niche that is unlikely to trigger for unrelated skills.	3 / 3
	Total	9 / 12 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning

	Total	15 / 16 Passed

Repository: SeemSeam/claude_codex_bridge
Path: inherit_skills/claude_skills/ask/SKILL.md
Commit: ec3de76

Reviewed: about 11 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.