Name: self-improvement
Rating: 67.2 (1 reviews)
Author: pskoett

self-improvement

Captures learnings, errors, corrections, and feature requests to enable continuous improvement. Use when: (1) User corrects Claude ('No, that's wrong...', 'Actually...'), (2) User requests a capability that doesn't exist, (3) Claude realizes its knowledge is outdated or incorrect, (4) A better approach is discovered for a recurring task, (5) Receiving a Handoff block from self-healing (a recurring verified heal at Recurrence-Count >= 3) to distill into a memory file or new skill. For ACTIVE runtime failures where the agent needs to apply and verify a fix mid-task, use `self-healing` instead (it files HEAL- entries with proof; self-improvement promotes accumulated patterns). Also review learnings before major tasks. For CI-only/headless learning capture, use self-improvement-ci.

Quality

81%

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

The canonical home for this skill is self-improvement in pskoett/pskoett-ai-skills

Quality

Content

75%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.

Highly actionable and clearly structured, with concrete templates, executable commands, and proper externalization of agent-specific detail into reference files. The main weakness is conciseness: the body is long and repeats some guidance Claude already knows.

Suggestions

Trim the Priority Guidelines and Area Tags tables (and the Best Practices list) to essentials or move them into a reference file; Claude already understands these concepts.

Reference references/examples.md from the body (e.g., link it from the Logging Format or Detection Triggers section) so the bundled examples file is discoverable rather than orphaned.

Consolidate the Install section's three installation variants and the Quick Setup/Full Setup hook blocks to reduce redundancy and token cost.

Dimension	Reasoning	Score
Conciseness	The body is well-organized but lengthy (~575 lines) with some padded explanatory prose and tables that restate what Claude already knows (e.g., explaining each priority level and area tag in prose); it could be tightened without losing clarity.	3 / 5
Actionability	Provides copy-paste-ready entry templates, concrete grep one-liners, exact hook JSON config, and executable extraction commands (extract-skill.sh with --dry-run); guidance is specific and runnable throughout.	5 / 5
Workflow Clarity	Multi-step processes (logging, recurring-pattern detection, skill extraction) are clearly sequenced with the explicit 3-condition promotion rule as a validation checkpoint and a quality-gate checklist; minor validation gaps in the logging/resolution flow keep it just below 5.	4 / 5
Progressive Disclosure	Good structure with well-signaled one-level-deep references to real bundle files (references/openclaw-integration.md, references/hooks-setup.md, assets/SKILL-TEMPLATE.md) plus the inline Quick Reference; the references/examples.md file is unreferenced from the body, a minor organization gap.	4 / 5
	Total	16 / 20 Passed

Description

88%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 strong, highly specific description with explicit what/when structure and numbered trigger conditions, plus useful disambiguation from sibling skills. Minor room to tighten the trigger phrasing toward the most natural user utterances.

Dimension	Reasoning	Score
Specificity	Names the domain ('continuous improvement') and enumerates multiple concrete actions: captures learnings, errors, corrections, feature requests, promotes recurring heal handoffs to memory files or new skills.	5 / 5
Completeness	Explicitly answers 'what' (captures learnings/errors/corrections/feature requests for continuous improvement and promotes recurring patterns) and 'when' (a five-item 'Use when' clause with concrete trigger phrases), and even disambiguates against the sibling self-healing and self-improvement-ci skills.	5 / 5
Trigger Term Quality	Includes natural user phrases ('No, that's wrong...', 'Actually...', 'I wish you could'-style feature requests) but relies more on paraphrased triggers than the full spread of synonyms and file extensions a 5 would require.	4 / 5
Distinctiveness Conflict Risk	Has a clear niche (passive accumulation/promotion) and explicitly contrasts it with self-healing's active runtime recovery and self-improvement-ci's headless path, though the broad term 'continuous improvement' leaves minor overlap risk with general learning skills.	4 / 5
	Total	18 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
skill_md_line_count	SKILL.md is long (579 lines); consider splitting into references/ and linking	Warning
relative_links	Relative link issues: 1 suspicious	Warning

	Total	14 / 16 Passed

Repository: pskoett/pskoett-ai-skills
Path: .agents/skills/self-improvement/SKILL.md
Commit: 8a71d70

Reviewed: 6 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.