improvement-workflow

Complete continuous improvement cycle orchestrating review, analysis, learning extraction, systematic updates, and validation. Sequential workflow from comprehensive review through pattern analysis and learning extraction to improvement application and re-validation. Use when continuously improving skills, applying review findings, implementing systematic enhancements, or executing complete improvement cycles.

Quality

71%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/improvement-workflow/SKILL.md

Quality

Content

60%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 well-structured orchestration workflow with a clear sequenced pipeline, explicit validation, and a feedback loop. Its main weaknesses are triplicate repetition of the same six steps, absence of executable code, and a few abstract sub-steps that lack concrete detail.

Suggestions

Collapse the redundant restatements: keep the step narratives, and let either the Quick Reference table OR the ASCII diagram carry the summary rather than both, to tighten conciseness.

Add one concrete, copy-paste-ready invocation example per step (e.g., the exact command or skill-call phrasing for 'Run review-multi comprehensive mode') to lift actionability.

Replace the obvious Best Practices 'Rationale' lines with a single terse justification or remove them, since Claude already understands why review-before-change and impact-prioritization matter.

Dimension	Reasoning	Score
Conciseness	Mostly efficient structural content, but the six steps are restated three times (narrative, Quick Reference table, ASCII diagram) and the Best Practices 'Rationale' lines restate the obvious, fitting anchor 3 rather than 4.	3 / 5
Actionability	Provides concrete steering to sub-skills and specific operations ('Run review-multi comprehensive mode', 'Use analysis Operation 5'), but contains no executable code or commands and several steps stay abstract ('Plan updates', 'Apply changes one at a time').	3 / 5
Workflow Clarity	Clear six-step sequence with an explicit validation step (Step 5 re-runs review-multi for before/after comparison) and a Post-Workflow feedback loop with revert guidance, but lacks a hard 'only proceed when valid' gate so it stops short of anchor 5.	4 / 5
Progressive Disclosure	No bundle files exist and all content is inline, but sections are well organized with a table and diagram for navigation; the ~240-line length and triplicate step repetition are minor organization gaps keeping it at anchor 4.	4 / 5
	Total	14 / 20 Passed

Description

83%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 strong: it explicitly covers both what the skill does and when to use it, with multiple concrete actions and natural trigger phrases. Its only weakness is that the named actions are orchestration-level rather than finely specific, leaving minor overlap and trigger-coverage gaps.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('review, analysis, learning extraction, systematic updates, and validation'), though they remain orchestration-level verbs rather than granular capabilities, matching anchor 4 with minor coverage gaps.	4 / 5
Completeness	Clearly states what the skill does (the full improvement cycle and its sequence) and provides an explicit 'Use when...' clause with concrete trigger phrases, satisfying both what and when.	5 / 5
Trigger Term Quality	Includes several natural trigger phrases ('continuously improving skills', 'applying review findings', 'implementing systematic enhancements', 'complete improvement cycles') with good keyword coverage, but misses a few common variations users might say.	4 / 5
Distinctiveness Conflict Risk	Targets a distinct skill-improvement orchestration niche with specific triggers, with only minor overlap risk against closely related review/updater skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning

	Total	15 / 16 Passed

Repository: fernandezbaptiste/Skrillz
Path: skills/improvement-workflow/SKILL.md
Commit: 93ed392

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.