CtrlK
BlogDocsLog inGet started
Tessl Logo

ask

Delegate work or request information from another CCB-managed agent using ask. Use when the user asks Grok to ask, delegate to, hand off to, consult, or send work to a named CCB agent, or when project memory requires CCB collaboration.

66

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./inherit_skills/grok_skills/ask/SKILL.md
SKILL.md
Quality
Evals
Security

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 skill body is a tight, actionable reference for the CCB ask command with a strong decision card and concrete command templates plus explicit after-submit and error-handling rules. Marginal gains are available by tightening a few explanatory guardrails and grounding the command examples with concrete values.

Suggestions

Replace one templated example with a concrete worked example (real target + message) so the common case is copy-paste ready.

Tighten the longer guardrail clauses into terse rules; move disambiguation detail into a short parenthetical only where ambiguity is real.

Add a one-line post-submit verification cue (e.g., how the caller confirms the task was accepted) to strengthen the workflow's checkpoint.

DimensionReasoningScore

Conciseness

The body is lean and rule-driven (Decision Card, terse guardrails, command blocks) with little padding, though a few guardrail clauses explain disambiguation (e.g., "Communication tests, batch sends... do not become chain dependencies merely because replies are requested") that could be trimmed.

4 / 5

Actionability

Provides concrete executable commands (the `command ask "$TARGET"` heredoc, the `--chain --artifact-reply` variant, and `ccb followup <active_job_id> --message`), but the examples are templates with placeholders rather than fully concrete copy-paste snippets covering common cases.

4 / 5

Workflow Clarity

A clear decision-then-submit-then-stop sequence is present with error-recovery guidance (retry once with plain ask on a chain error; report not-submitted on permission denial), but there is no explicit validate/verify checkpoint, which is acceptable since ask is not a destructive or batch operation.

4 / 5

Progressive Disclosure

Content is well-organized under clear headers (Decision Card, Guardrails, command examples) in a single self-contained file with no external references; it sits just over the 50-line simple-skill threshold, so the 5-anchor simple-skill exception does not apply.

4 / 5

Total

16

/

20

Passed

Description

82%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 clearly answers what and when with a distinct CCB-delegation niche and strong trigger phrasing. Its only weakness is that the concrete capability list is narrow (delegate vs. request) while the rest of the verb list serves as triggers.

Suggestions

Promote one or two of the trigger verbs into stated capabilities (e.g., "Delegate work, consult, or hand off tasks") so the what-clause reads as multiple concrete actions rather than two.

Consider adding a brief outcome framing (e.g., "returns a routed task result") so the capability is distinguishable from generic messaging.

DimensionReasoningScore

Specificity

Names the domain and two concrete actions ("Delegate work or request information"), but the trailing verb list (ask/delegate/hand off/consult/send work) are trigger phrasings rather than distinct capabilities, so coverage is not comprehensive.

3 / 5

Completeness

Explicitly states both what it does ("Delegate work or request information from another CCB-managed agent using ask") and when to use it ("Use when the user asks Grok to ask, delegate to, hand off to... or when project memory requires CCB collaboration") with concrete triggers.

5 / 5

Trigger Term Quality

Includes several natural phrases a user would say ("ask, delegate to, hand off to, consult, or send work to a named CCB agent"), giving good synonym coverage, though a few common variations are absent.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche (delegation to a named CCB-managed agent) with distinct triggers, so overlap with unrelated skills is minimal.

5 / 5

Total

17

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
SeemSeam/claude_codex_bridge
Reviewed

Table of Contents

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.