CtrlK
BlogDocsLog inGet started
Tessl Logo

system-reviewer

Review the skill development ecosystem itself - assess ecosystem health, identify systemic issues, evaluate toolkit effectiveness, and recommend system-level improvements. Task-based operations for ecosystem assessment, toolkit evaluation, process review, and system optimization. Use when evaluating ecosystem health, identifying systemic improvements, optimizing the toolkit itself, or conducting meta-level ecosystem reviews.

55

Quality

62%

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 ./skills/system-reviewer/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

50%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 well-structured with consistent per-operation process steps and a useful quick-reference table, but it is verbose and operates at an abstract directive level without executable specifics or validation checkpoints. Splitting the five operation guides and example into reference files would improve both conciseness and progressive disclosure.

Suggestions

Split each of the five operation sections (and the illustrative ecosystem-health report) into separate reference files linked from a lean SKILL.md overview to reduce inline bulk and improve progressive disclosure.

Add explicit validation/verification checkpoints to each operation's process (e.g., 'after running review-multi on all skills, confirm every skill returned a valid score before aggregating') to support batch operations.

Replace abstract directives like 'Run review-multi validation on all skills' with the concrete command or workflow invocation to execute, making the guidance copy-paste actionable.

DimensionReasoningScore

Conciseness

The body is organized and avoids explaining basic concepts, but it is noticeably long (~390 lines) with a repeated five-step pattern across five operations and a 50+ line illustrative report that could be tightened.

3 / 5

Actionability

Each operation lists concrete metrics and steps plus an example output template, but guidance stays at a high directive level ('Run review-multi validation on all skills', 'Calculate average quality scores') without specific commands or scripts to execute.

3 / 5

Workflow Clarity

Every operation has a clearly numbered five-step Process, but the steps lack explicit validation/verification checkpoints; running validation across all skills is a batch operation with no validate-fix-retry feedback loop, capping the score.

3 / 5

Progressive Disclosure

Section headers and a Quick Reference table provide reasonable structure, but all content is inlined in one ~390-line file with no bundle files; the five detailed operation guides and example report would benefit from being split into separate references.

3 / 5

Total

12

/

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.

A well-constructed description with explicit third-person action verbs and a clear 'Use when...' trigger clause covering multiple scenarios. It is mostly distinct from individual-skill review skills, with only minor abstraction in the 'what' actions keeping it just below top marks.

DimensionReasoningScore

Specificity

Lists several concrete actions ('assess ecosystem health, identify systemic issues, evaluate toolkit effectiveness, and recommend system-level improvements'), though the actions remain somewhat abstract/meta rather than fully concrete operations.

4 / 5

Completeness

Both 'what' (the four review actions) and 'when' (explicit 'Use when...' clause) are present; the 'when' is concrete, but the 'what' actions are slightly abstract compared to the fully concrete 5-anchor example.

4 / 5

Trigger Term Quality

The 'Use when...' clause supplies multiple natural trigger phrases ('evaluating ecosystem health, identifying systemic improvements, optimizing the toolkit itself'), but 'meta-level ecosystem reviews' is jargon and common synonyms are missing.

4 / 5

Distinctiveness Conflict Risk

The 'ecosystem itself' / 'meta-level' framing carves a clear niche distinct from individual-skill review, with minor overlap risk against a general skill-reviewer; not a perfectly isolated trigger set.

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.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

Total

15

/

16

Passed

Repository
fernandezbaptiste/Skrillz
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.