consult-claude

Run Claude Code as an independent reviewer or research laboratory while you keep ownership of the live repository. Use when the user asks to consult Claude, requests a Claude review, or asks Claude to investigate or research independently.

Quality

76%

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 ./.agents/skills/consult-claude/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 body delivers executable commands and a clear consultation workflow with state-based checkpoints while staying concise and not over-explaining known concepts. Adding section headers and a brief example of a research brief would push the structure and actionability closer to ideal.

Suggestions

Add section headers (e.g., ## Start, ## Read results, ## Follow up) so the workflow stages are navigable at a glance.

Include a short example research brief to make the 'type the compact research brief, then send EOF' step concrete and copy-paste ready.

Tighten the opening conceptual framing ('sealed laboratory' / 'living checkout') to its essential boundary statement to recover a few tokens without losing the model.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence, avoiding explanations of known concepts; the 'sealed laboratory' framing is purposeful boundary modeling but is slightly prose-heavy and could be trimmed, keeping it just below the lean-and-efficient anchor of 5.	4 / 5
Actionability	It provides concrete, copy-pasteable commands (`start --wait`, `status <run-id>`, `follow-up --wait`) and notes what each prints, covering the main workflow with minor gaps such as no example research-brief content.	4 / 5
Workflow Clarity	The start -> status -> follow-up sequence is clearly ordered with state-based checkpoints (`state: needs-decision`, `state: complete`) and re-verification guidance, satisfying most checkpoints with only minor validation gaps.	4 / 5
Progressive Disclosure	A single overview SKILL.md references one clearly-signaled, one-level-deep script (scripts/consult-claude.ts, confirmed present in the bundle); structure is good but lacks section headers that would improve navigation, so it sits just below the well-organized anchor of 5.	4 / 5
	Total	16 / 20 Passed

Description

78%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 cleanly states both the capability and concrete usage triggers in third person, with strong completeness and good natural trigger terms. Specificity is slightly limited because the actions are framed at the role level rather than as an enumerated set of concrete operations.

Dimension	Reasoning	Score
Specificity	Names the domain and 1-2 concrete roles ('independent reviewer or research laboratory') but does not enumerate a comprehensive set of specific actions, matching the anchor for 1-2 concrete actions without comprehensive coverage.	3 / 5
Completeness	It explicitly answers both what ('Run Claude Code as an independent reviewer or research laboratory while you keep ownership of the live repository') and when ('Use when the user asks to consult Claude, requests a Claude review, or asks Claude to investigate or research independently') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural user-facing phrases are present ('consult Claude', 'Claude review', 'investigate', 'research independently'), giving good keyword coverage with only minor synonymous variations missing.	4 / 5
Distinctiveness Conflict Risk	The independent-consultation niche and 'consult Claude' trigger are mostly distinct with minimal conflict risk, though there is minor overlap potential with general code-review skills, so it does not reach the clearly-minimal-risk anchor of 5.	4 / 5
	Total	16 / 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: EpicenterHQ/epicenter
Path: .agents/skills/consult-claude/SKILL.md
Commit: 9e1f9d2

Reviewed: 1 day 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.