CtrlK
BlogDocsLog inGet started
Tessl Logo

cavecrew

When to delegate to `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit) or `cavecrew-reviewer` (diff review) instead of working inline or using `Explore`. Their output is compressed, so main context lasts longer.

64

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/caveman/skills/cavecrew/SKILL.md

The canonical home for this skill is cavecrew in JuliusBrussee/caveman

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 body is a compact, highly structured delegation guide with concrete output contracts, chaining patterns, and guardrails rather than filler. It is actionable and well-sequenced, with only minor room to tighten rationale and formalize validation feedback loops.

DimensionReasoningScore

Conciseness

Lean, table-and-template driven body that assumes Claude's competence and avoids explaining basic concepts; the 'Why this exists' rationale adds one mildly explanatory paragraph, keeping it at 4 rather than a fully trimmed 5.

4 / 5

Actionability

Concrete output-contract templates and named chaining recipes (locate→fix→verify, parallel scout, single-shot) are copy-paste-ready and cover common cases; minor gaps (e.g. exact mechanics of parallel spawning) hold it at 4.

4 / 5

Workflow Clarity

The locate→fix→verify pattern is a clearly sequenced multi-step flow with an explicit verify checkpoint (reviewer audits the diff); not quite a full validate→fix→retry feedback loop with error-recovery detail, so 4 rather than 5.

4 / 5

Progressive Disclosure

Well-organized into clear sections (comparison table, output contracts, chaining, anti-patterns) with no unnecessary external references for a self-contained guide; minor inlining of dense contract blocks keeps it at 4 over 5.

4 / 5

Total

16

/

20

Passed

Description

75%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 concise and clearly signals both what the skill does and when to use it, with explicit alternatives for comparison. It is specific and distinctive but stops just short of comprehensive trigger-phrase coverage.

DimensionReasoningScore

Specificity

Names three concrete agents with concrete tasks (`cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), `cavecrew-reviewer` (diff review)) — several specific actions with only minor gaps in coverage, fitting the 4 anchor rather than 5's comprehensive list.

4 / 5

Completeness

Answers both 'what' (three delegation targets returning compressed output) and 'when' ('When to delegate ... instead of working inline or using `Explore`'); the when is explicit but could be slightly more trigger-phrase specific, matching 4 over 5.

4 / 5

Trigger Term Quality

Includes natural terms like 'locate code', '1-2 file edit', 'diff review', and 'Explore' that users would plausibly say; a few common synonyms (e.g. 'search', 'find references') are missing, so it sits at 4 rather than 5.

4 / 5

Distinctiveness Conflict Risk

Clear niche (compressed caveman-output subagents) with explicit differentiation from vanilla `Explore`/`Code Reviewer`; minor overlap risk with general delegation skills keeps it at 4 rather than 5.

4 / 5

Total

16

/

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
JuliusBrussee/caveman
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.