ask

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

Quality

64%

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

75%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 content is a tight, actionable, well-structured operational guide that assumes Claude's competence and gives concrete command templates plus a decision workflow. It sits solidly at 4 across dimensions, held from 5 by placeholder-based examples, light explicit validation, and the absence of any file-split references.

Suggestions

Add one fully-resolved worked example with concrete `$TARGET` and `$MESSAGE` values to make the command templates copy-paste ready.

Consolidate the repeated `--chain` guidance across the Guardrails section to tighten conciseness.

Add an explicit validation checkpoint after the ask returns (e.g. confirm the receipt shape before ending the turn) to strengthen workflow clarity.

Dimension	Reasoning	Score
Conciseness	The body is dense and operational with no padding or explanation of concepts Claude already knows; each guardrail earns its place, though a few chain-related rules repeat and could be consolidated, fitting the efficient-with-minor-trim anchor rather than the perfectly lean 5.	4 / 5
Actionability	Provides concrete, copy-paste command templates (`command ask "$TARGET" <<'EOF'...EOF`) and a precise receipt schema mapping intents to specific flags, but examples rely on `$TARGET`/`$MESSAGE` placeholders and not every flag combination is exemplified, so it is mostly rather than fully executable.	4 / 5
Workflow Clarity	The Decision Card gives a clear sequenced workflow (delegation need -> dependency gate -> result intent -> request fidelity) with error-recovery guidance (retry plain `ask` on `--chain` rejection) and a receipt checklist; the destructive/batch cap does not apply since delegation is not destructive, but explicit validation checkpoints are lighter than the 5 anchor.	4 / 5
Progressive Disclosure	No bundle files exist and the single SKILL.md is well-organized into clearly headed sections (Decision Card, Guardrails, Kimi Receipt Contract) with easy navigation; because the skill exceeds 50 lines it does not qualify for the simple-skill 5, landing at the good-structure anchor.	4 / 5
	Total	16 / 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 is concrete and clearly distinct but terse: it states what the skill does without any explicit when-to-use trigger guidance, which caps completeness. Adding a "Use when delegating to a CCB agent..." clause would lift the weakest dimension.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user asks you to delegate work to a CCB agent or when project memory says to use CCB `ask`."

Include natural synonyms users might say ("delegate", "hand off to CCB", "ask another agent") to improve trigger term coverage.

Mention 1-2 more concrete actions (e.g. routing results, preserving artifacts) to push specificity above 3.

Dimension	Reasoning	Score
Specificity	Names a concrete action ("Send a request") and the specific mechanism (`ask`) with its target ("a CCB agent"), matching the anchor that names a domain with 1-2 concrete actions; it stops short of the multiple specific actions needed for a 4.	3 / 5
Completeness	It states clearly what the skill does ("Send a request to a CCB agent with `ask`") but provides no "Use when..." trigger clause, so per the boundary guidance completeness is capped at 3 (clear what, missing when).	3 / 5
Trigger Term Quality	Relevant keywords ("request", "CCB agent", "ask") appear but common natural-language variations a user might say (e.g. "delegate", "hand off", "ask CCB") are absent, fitting the anchor with some relevant keywords missing synonyms.	3 / 5
Distinctiveness Conflict Risk	The proprietary CCB `ask` niche is clearly distinct from generic skills with only minor overlap risk against other CCB-family skills, fitting the "mostly distinct" anchor rather than the fully distinct 5.	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: 01d5b1c

Reviewed: about 20 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.