CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-improvement-from-observability

Complete feedback loop from observability insights to skill updates. Use when analyzing enhanced telemetry patterns and automatically improving skills.

56

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.claude/skills/skill-improvement-from-observability/SKILL.md

The canonical home for this skill is skill-improvement-from-observability in fernandezbaptiste/Skrillz

SKILL.md
Quality
Evals
Security

Quality

Content

63%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 highly actionable with concrete queries and a clear numbered workflow plus safety gating, but it is monolithic and carries redundant query blocks that inflate the token budget. Splitting the query library into a reference file would improve both conciseness and progressive disclosure.

Suggestions

Move the 'Key Queries for Improvement Analysis' block into a references/ file (e.g. QUERIES.md) and link to it, eliminating the duplicate queries in section 3.

Add an explicit validation checkpoint before 'skill-updater applies changes' (e.g., dry-run or review-multi validation) to raise workflow_clarity toward 5.

Replace placeholder/non-standard filters like '<pattern_filter>' and 'previous_tool="Read" and tool_name="Read"' with verified LogQL syntax or annotate them as illustrative.

DimensionReasoningScore

Conciseness

The body is mostly executable LogQL/JSON rather than concept explanation, but error-rate queries are repeated across section 3 and 'Key Queries for Improvement Analysis', and the three illustrative flows are somewhat redundant.

3 / 5

Actionability

Concrete, copy-paste-ready LogQL queries, a recommendation JSON template, and a pattern-to-skill mapping table provide mostly executable guidance; minor gaps like the '<pattern_filter>' placeholder and the non-standard 'previous_tool=' filter keep it just below 5.

4 / 5

Workflow Clarity

A clear 6-step sequence (collect → detect → extract → map → generate → track) is present with the Safety Classification acting as a review checkpoint and 'Track Effectiveness' as a feedback loop, though an explicit pre-deploy validation step is only implied.

4 / 5

Progressive Disclosure

Sections are well-organized, but the skill is a monolithic ~230-line file with no reference bundle and a large inlined query library that would benefit from a separate reference file.

3 / 5

Total

14

/

20

Passed

Description

62%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 states both what the skill does and when to use it, with a well-defined niche around observability-driven skill improvement. It would benefit from more natural trigger phrasing and a broader set of concrete action verbs.

Suggestions

Add natural-language trigger terms a user would actually say (e.g., 'telemetry', 'skill performance', 'error patterns') alongside the technical 'enhanced telemetry patterns'.

List more concrete actions (e.g., 'detect failure patterns', 'generate improvement recommendations', 'validate changes') to raise specificity from 3 toward 5.

DimensionReasoningScore

Specificity

Names the domain ('observability insights to skill updates') and 1-2 concrete actions ('analyzing enhanced telemetry patterns', 'automatically improving skills'), but 'feedback loop' is conceptual and coverage is not comprehensive.

3 / 5

Completeness

Both 'what' ('Complete feedback loop from observability insights to skill updates') and an explicit 'when' ('Use when analyzing enhanced telemetry patterns and automatically improving skills') are present, though the trigger could be more specific.

4 / 5

Trigger Term Quality

Relevant keywords like 'telemetry patterns' and 'observability insights' appear, but they lean technical and omit common synonyms a user would naturally say; not the level-4 natural-phrase coverage.

3 / 5

Distinctiveness Conflict Risk

The observability-driven skill-improvement niche is fairly distinct, with only minor overlap risk from the broad phrase 'improving skills'.

4 / 5

Total

14

/

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
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.