CtrlK
BlogDocsLog inGet started
Tessl Logo

self-improvement

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

81

4.21x
Quality

74%

Does it follow best practices?

Impact

97%

4.21x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./clawdbot/self-improving-agent/SKILL.md

The canonical home for this skill is self-improving-agent in jdrhyne/agent-skills

SKILL.md
Quality
Evals
Security

Quality

Content

52%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 highly actionable with concrete templates, commands, and hook configs, and workflows are reasonably well-sequenced. It is held back by significant verbosity (repeated trigger sections, self-explanatory tables) and a broken progressive-disclosure structure where referenced bundle files do not exist.

Suggestions

De-duplicate the trigger guidance: keep the Quick Reference table and remove the redundant Detection Triggers and Extraction Detection Triggers prose, or consolidate them into a single section.

Create the referenced bundle files (assets/SKILL-TEMPLATE.md, scripts/activator.sh, scripts/error-detector.sh, scripts/extract-skill.sh, references/hooks-setup.md) and move the inlined hook-config JSON and full templates out of SKILL.md into them so the overview stays lean.

Trim or remove self-explanatory tables (Priority Guidelines, Area Tags) that restate concepts Claude already knows, keeping only project-specific conventions.

DimensionReasoningScore

Conciseness

The ~500-line body is noticeably verbose: trigger content is repeated across the Quick Reference table, the Detection Triggers section, and again under Extraction Detection Triggers, and self-explanatory tables (Priority Guidelines, Area Tags) pad sections Claude already understands.

2 / 5

Actionability

Provides concrete, mostly copy-paste-ready templates for learning/error/feature entries, executable bash (grep review, mkdir, extract-skill.sh), and full hook JSON configs; minor gap is that activator.sh and error-detector.sh are named but not shown.

4 / 5

Workflow Clarity

Logging, resolving, promoting, and extracting workflows are numbered and sequenced with checkpoints (e.g., 'Verify: Read skill in fresh session', Skill Quality Gates checklist); the core logging operation is append-only/non-destructive so the missing-validation cap does not apply.

4 / 5

Progressive Disclosure

The body is a monolithic ~500-line document and references assets/, scripts/, and references/hooks-setup.md, but none of those bundle files exist, so detailed material that belongs in separate files is either inlined or points at missing paths, breaking navigation.

2 / 5

Total

12

/

20

Passed

Description

96%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 concisely states the skill's purpose and provides an explicit, enumerated set of natural trigger conditions including quoted user speech. Only minor distinctiveness overlap with general memory skills keeps it from a perfect score across all dimensions.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ('Captures learnings, errors, and corrections') alongside six distinct capture scenarios, giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers 'what' (captures learnings, errors, and corrections for continuous improvement) and 'when' via six numbered concrete triggers plus 'review learnings before major tasks'.

5 / 5

Trigger Term Quality

Includes natural user phrases users actually say, such as quoted corrections ('No, that's wrong...', 'Actually...') and 'A command or operation fails unexpectedly', covering synonyms and real conversational triggers.

5 / 5

Distinctiveness Conflict Risk

The self-improvement / error-logging niche is mostly distinct with specific triggers, but has minor overlap risk with generic memory or journaling skills.

4 / 5

Total

19

/

20

Passed

Validation

87%

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

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

skill_md_line_count

SKILL.md is long (501 lines); consider splitting into references/ and linking

Warning

referenced_paths_exist

Referenced path issues: 4 missing

Warning

Total

14

/

16

Passed

Repository
bap-jorkim/agent-skills-fork-feb-25
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.