ask

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

Quality

60%

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 ./inherit_skills/kimi_skills/ask/SKILL.md

Quality

Content

67%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 well-structured, highly actionable operational guide for CCB ask delegation, with concrete command templates and error-recovery loops. Its main weakness is redundancy in the guardrails, where chain/silence/continuation rules are repeated in overlapping forms.

Suggestions

Consolidate the overlapping --chain/--silence/continuation guardrail bullets into a single routing table (situation -> flags) to remove restated rules.

Clarify whether "command" in the templates is a literal prefix or a placeholder, and show how $TARGET and $MESSAGE are populated.

Add a brief post-submit verification step (beyond "end the turn") so the workflow has an explicit final checkpoint.

Dimension	Reasoning	Score
Conciseness	The body is dense CCB-specific knowledge Claude does not already know, but the Guardrails section restates --chain/--silence/continuation-routing rules across several overlapping bullets (e.g. "Do not probe --chain", "Never add --chain merely...", "Plain nested ask... Use --chain only for a real child dependency", "If the current task is a CCB result-chain continuation...") that could be merged. Mostly efficient but could be tightened, matching anchor 3 rather than 4 where over-explanation would be only minor.	3 / 5
Actionability	Concrete executable templates are provided (the heredoc "command ask \"$TARGET\" <<'EOF'" forms, exact flag combinations, the receipt field template, and "ccb followup <active_job_id> --message ..."), giving mostly executable guidance. Not anchor 5 because $TARGET/$MESSAGE placeholder resolution and the odd literal "command" prefix leave minor gaps.	4 / 5
Workflow Clarity	The Decision Card gives an explicit 4-step sequence (delegation, dependency gate, result intent, request fidelity), and guardrails include feedback loops (retry once with plain ask on the chain error; cancel and resubmit on rejected/too_late/terminal). Not anchor 5 because the full ask lifecycle lacks an explicit post-submit validation checkpoint.	4 / 5
Progressive Disclosure	No bundle files exist, and the body is organized into clear, well-labeled sections (Decision Card, Guardrails, Kimi Receipt Contract, command templates). It exceeds the under-50-line simple-skill exception due to the long guardrail list that could partly live in a reference file, matching anchor 4 rather than 5.	4 / 5
	Total	15 / 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 states a clear, distinct action but is minimal: it lacks any "when to use" trigger guidance and omits natural synonyms like "delegate". It sits at the midpoint of most dimensions.

Suggestions

Append an explicit trigger clause, e.g. "Use when the user asks to delegate or consult another agent, or when project memory says to use CCB ask for collaboration."

Add natural trigger terms such as "delegate", "hand off", or "consult an agent" alongside "send a request".

Mention the main capability variations (e.g. chained delegation, silent fire-and-forget, artifact-based exchange) to raise specificity from one action to several.

Dimension	Reasoning	Score
Specificity	"Send a request to a CCB agent" names the domain and one concrete action, matching the anchor for 1-2 concrete actions without comprehensive coverage. It is above anchor 2 (generic minimal action) but below anchor 4, which requires several listed specific actions.	3 / 5
Completeness	The "what" is clear (send a request to a CCB agent with ask), but the description contains no "Use when..." clause or equivalent trigger guidance, which the judging guidelines cap at 3. Not anchor 4 because "when" is entirely absent rather than merely implicit.	3 / 5
Trigger Term Quality	Relevant keywords like "CCB agent", "request", and "ask" are present, but common natural variations users would say ("delegate", "hand off", "collaborate with another agent") are missing. Not anchor 4 because keyword coverage is not good enough.	3 / 5
Distinctiveness Conflict Risk	"CCB" and "ask" form a clear niche with distinct triggers and minimal conflict risk against generic file/document skills. Not anchor 5 because the description could still overlap with other agent-delegation skills that also trigger on "request to an agent".	4 / 5
	Total	13 / 20 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/kimi_skills/ask/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.