CtrlK
BlogDocsLog inGet started
Tessl Logo

cavecrew

Decision guide for delegating to caveman-style subagents. Tells the main thread WHEN to spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), or `cavecrew-reviewer` (diff review) instead of doing the work inline or using vanilla `Explore`. Subagent output is caveman-compressed so the tool-result injected back into main context is ~60% smaller — main context lasts longer across long sessions. Trigger: "delegate to subagent", "use cavecrew", "spawn investigator/builder/reviewer", "save context", "compressed agent output".

77

Quality

96%

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

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

SKILL.md
Quality
Evals
Security

Quality

Content

100%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 tight, highly actionable decision guide with concrete output contracts, sequenced chaining patterns, built-in validation/feedback signals, and clean section organization. It assumes Claude's competence and avoids verbosity.

DimensionReasoningScore

Conciseness

Lean and efficient throughout — assumes Claude knows what subagents and `Explore` are, with every section (decision table, output contracts, chaining patterns) earning its tokens; no padding or basic-concept explanations.

5 / 5

Actionability

Provides exact output-contract templates per agent, a concrete decision table, and numbered chaining patterns — fully actionable guidance covering the common delegation cases.

5 / 5

Workflow Clarity

The locate→fix→verify chaining pattern is explicitly sequenced with a validation checkpoint (reviewer audits the diff), and output contracts include feedback loops (verified field, terminal tokens like `too-big.`/`regressed.`) for error recovery.

5 / 5

Progressive Disclosure

Self-contained with no external bundle files needed; content is organized into clearly signaled sections (When to use, Output contracts, Chaining patterns, What NOT to do) with no nested references.

5 / 5

Total

20

/

20

Passed

Description

92%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 specific, complete, and distinctive, clearly stating both what the skill does and when to use it with concrete trigger phrases. Trigger-term coverage is strong but includes one technical phrase and could add a few more natural synonyms.

DimensionReasoningScore

Specificity

Names the domain and lists three concrete, distinct actions — spawn `cavecrew-investigator` (locate code), `cavecrew-builder` (1-2 file edit), `cavecrew-reviewer` (diff review) — giving comprehensive coverage of the skill's capabilities.

5 / 5

Completeness

Explicitly answers what (decision guide for delegating to caveman-style subagents with three named agents) and when (a dedicated Trigger clause with concrete phrases), matching the top anchor.

5 / 5

Trigger Term Quality

Provides several natural trigger phrases ("delegate to subagent", "use cavecrew", "save context") that users would plausibly say, though "compressed agent output" skews technical and a few natural synonyms are absent.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (compressed caveman subagents) with distinctive named triggers and explicit differentiation from vanilla `Explore`/`Code Reviewer`, giving minimal conflict risk.

5 / 5

Total

19

/

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.