CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

consult-claude

Give Claude Opus 5.5 responsibility for reasoning, design judgment, read-only investigations, recommendations, or finished text drafts. Use when the result benefits from thoughtful reasoning or taste, when asked to consult Claude, or when supplying the Claude seat of an independent review. Completed edits and executable experiments belong to delegate-claude.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Medium

Suggest reviewing before use

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/consult-claude/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.

A highly actionable skill with copy-paste-ready launcher commands, explicit result-validation checkpoints, and well-signaled one-level-deep references. Its weaknesses are repetition and density in the body — defaults and boundary-reapplication stated multiple times, and account/auth mechanics inlined that could be split out.

Suggestions

State the model/effort default once and reference it elsewhere; the same Opus-5.5-high default appears in both 'Send a brief' and the launcher-defaults paragraph, and 'the launcher reapplies the boundary/tools' recurs across the resume section.

Move the multi-account login mechanics (Keychain behavior, CLAUDE_CONFIG_DIR guidance, browser login steps) into a short reference file linked from 'Choose a subscription account', keeping the body to the launch-time essentials.

Add brief guidance on what to do when the native result reports is_error or permission denials, so the validation checkpoint has a matching recovery step.

DimensionReasoningScore

Conciseness

The body is dense and free of concepts Claude already knows, but it could be tightened: model/effort defaults are stated twice ("New and resumed consultations default to claude-opus-5-5 at high effort" and later "New consultations, delegations and resumes use Opus 5.5 high unless explicit --model or --effort flags override them"), and launcher boundary-reapplication is repeated across the resume section ("The launcher reapplies read-only tools", "The launcher reapplies the access boundary on every turn"). This matches 'mostly efficient but could be tightened'; it avoids 2 because there is no padded conceptual explanation, and misses 4 because the redundancy and convoluted policy sentences are more than minor.

3 / 5

Actionability

Fully executable, copy-paste-ready commands cover the common cases: the launcher invocation with account, model, and effort flags and a heredoc brief; the resume command with --resume <session_id>; the work-login command (CLAUDE_CONFIG_DIR=... claude auth login --claudeai --email ...); and --dry-run for previewing. A concrete example brief and a checklist of what to record in task notes make the guidance specific, matching the top anchor.

5 / 5

Workflow Clarity

The sections sequence a clear workflow (define result → make design legible → send brief → check result → adjudicate/continue) with explicit checkpoints: read the native JSON result including is_error and permission denials, treat sandboxed auth status as inconclusive, and verify session identity before resuming. It falls short of 5 because error-recovery loops are thinner — what to do when is_error is true or a permission denial appears is noticed but not acted out — matching 'clear sequence with most checkpoints present; minor validation gaps'.

4 / 5

Progressive Disclosure

The bundle is well used: both references/ files exist and are clearly signaled with purpose and timing ("Read [Codex assistance](references/codex-assistance.md) before enabling it", "Read [the example and evaluation cases](references/example-workflow.md) when evaluating this workflow"), references are one level deep, and scripts are invoked rather than inlined. Not 5 because the ~225-line body inlines operational detail (multi-account login mechanics, the macOS Keychain sandbox quirk, review-delivery logistics) that could live in a reference, leaving the overview heavier than it needs to be.

4 / 5

Total

16

/

20

Passed

Description

76%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.

A strong description that clearly states both capability and explicit 'Use when' triggers, and even disambiguates from a sibling skill. The main gap is trigger-term coverage: beyond the verbatim "consult Claude", the activation conditions are abstract rather than the natural phrasings users would utter.

Suggestions

Add one or two natural trigger variations such as 'get Claude's opinion' or 'ask Claude to review' to the 'Use when' clause so it matches how users actually phrase the request.

DimensionReasoningScore

Specificity

Quotes several concrete responsibilities — "read-only investigations, recommendations, or finished text drafts" — which name specific deliverable types for this niche. It falls short of 5 because "reasoning, design judgment" are abstract capabilities rather than concrete actions, and above 3 because multiple distinct action types are explicitly listed.

4 / 5

Completeness

Explicitly answers both questions: what ("Give Claude Opus 5.5 responsibility for reasoning, design judgment, read-only investigations, recommendations, or finished text drafts") and when, via an explicit "Use when..." clause with three concrete trigger conditions. It also adds a routing boundary ("Completed edits and executable experiments belong to delegate-claude"), which exceeds the 4 anchor whose 'when' is less explicit.

5 / 5

Trigger Term Quality

"when asked to consult Claude" and "independent review" are natural phrases a user would say, but the remaining triggers ("when the result benefits from thoughtful reasoning or taste", "supplying the Claude seat") are semantic conditions rather than keywords. Common variations like "get Claude's opinion", "ask Claude", or "second opinion" are missing, matching the anchor for relevant-but-incomplete keyword coverage.

3 / 5

Distinctiveness Conflict Risk

The read-only consultation niche is clear and the description actively disambiguates from the closest sibling ("Completed edits and executable experiments belong to delegate-claude"), reducing conflict risk. Not 5 because the domain of "reasoning, design judgment, recommendations" is inherently broad and could still overlap with general advisory or review skills beyond the explicitly handled ones.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

CriteriaDescriptionResult

relative_links

Relative link issues: 2 suspicious

Warning

Total

15

/

16

Passed

Repository

EpicenterHQ/epicenter

Path

.agents/skills/consult-claude/SKILL.md

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.