CtrlK
BlogDocsLog inGet started
Tessl Logo

caveman-stats

Show real token usage and estimated savings for the current session. Reads directly from the Claude Code session log — no AI estimation. Triggers on /caveman-stats. Output is injected by the mode-tracker hook; the model itself does not compute the numbers.

66

Quality

79%

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 ./.agents/skills/caveman-stats/SKILL.md

The canonical home for this skill is caveman-stats in JuliusBrussee/caveman

SKILL.md
Quality
Evals
Security

Quality

Content

92%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 content is a tight, well-structured explanation of a passive hook-delivered skill that correctly tells the model it needs to do nothing. It is appropriately concise and clear; the only minor gap is the absence of any executable snippet, which is acceptable given the no-op nature of the skill.

DimensionReasoningScore

Conciseness

The body is a lean three sentences with no padding and no explanation of concepts Claude already knows, matching the 'lean and efficient; assumes Claude's competence; every token earns its place' anchor; it is not lower because there is no unnecessary explanation to trim.

5 / 5

Actionability

It gives concrete guidance naming the delivering file, the reader hook, and the 'decision: block' contract, which is mostly executable and specific; it is not a 5 because there are no copy-paste examples, and not a 3 because the mechanism is concrete rather than pseudocode-level.

4 / 5

Workflow Clarity

This is a simple single-purpose no-op skill where the model's sole action (do nothing; the hook handles output) is unambiguous, qualifying for the simple-skill exception that lets a clear single action score 5; no destructive or batch operation is present to invoke the workflow cap.

5 / 5

Progressive Disclosure

The body is under 50 lines, requires no external references, and is well-organized as a single clear paragraph, matching the guideline that simple skills with no need for external references can score 5 with well-organized content; it is not lower because no content belongs in a separate file.

5 / 5

Total

19

/

20

Passed

Description

66%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 and concisely states what the skill does and when it fires, with a distinct niche and low conflict risk. Its main weakness is limited natural trigger-term coverage beyond the single '/caveman-stats' command.

Suggestions

Add natural-language trigger phrases users might say (e.g., 'Use when the user asks about token usage, session costs, or how many tokens have been consumed') to lift trigger-term coverage and completeness.

List a couple more concrete outputs/actions (e.g., 'reports total input/output tokens and estimated cost savings') to broaden specificity beyond the single core action.

DimensionReasoningScore

Specificity

Names the domain ('token usage and estimated savings') and a concrete mechanism ('Reads directly from the Claude Code session log — no AI estimation'), which matches the anchor listing 1-2 concrete actions; it does not enumerate the multiple specific actions needed for a 4 or 5.

3 / 5

Completeness

It states a clear 'what' ('Show real token usage and estimated savings') and an explicit 'when' ('Triggers on /caveman-stats'), matching the anchor where both are present but the 'when' could be more specific; it is not a 5 because the trigger is a single slash command rather than concrete natural trigger phrases, and not a 3 because 'when' is genuinely stated.

4 / 5

Trigger Term Quality

It includes some relevant natural terms ('token usage', 'estimated savings', 'session log') and a literal '/caveman-stats' trigger, but coverage of natural phrasings users would say is limited to one trigger path, fitting the 'some relevant keywords but missing common variations' anchor rather than the fuller coverage of a 4.

3 / 5

Distinctiveness Conflict Risk

It carves a clear niche — session token-usage stats delivered via a named hook on a specific slash command — with minimal overlap risk against other skills, matching the 'clear niche with distinct triggers; minimal conflict risk' anchor.

5 / 5

Total

15

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
masweb/waxp-vuebo
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.