CtrlK
BlogDocsLog inGet started
Tessl Logo

self-improving-agent

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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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.

60

Quality

70%

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

Fix and improve this skill with Tessl

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

Quality

Content

50%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

This is a well-intentioned skill with clear structure and useful record-type templates, but it's somewhat verbose for what it accomplishes. The main weaknesses are the lack of executable commands for file/directory creation, missing validation checkpoints in the workflow, and inline templates that could benefit from being extracted to a separate reference file. The safety boundaries section is a genuine strength.

Suggestions

Add executable shell commands for initial setup (e.g., `mkdir -p .learnings` and file creation) and provide a concrete example of appending an entry to an existing file.

Add a validation step to the workflow, such as checking that the entry ID is unique and the file was written successfully before considering the logging complete.

Extract the three full record-type templates into a separate TEMPLATES.md file and reference it from the main skill, keeping only a brief summary of each type inline.

Clarify how to generate the sequential XXX portion of entry IDs (e.g., auto-increment by scanning existing entries or use a simple counter).

DimensionReasoningScore

Conciseness

The skill is reasonably efficient but includes some redundancy. The record type templates are verbose with full markdown examples that could be more compact. The 'When to Use' section partially overlaps with the description. However, the templates do provide genuinely useful structure that Claude wouldn't inherently know.

2 / 3

Actionability

The templates provide concrete structure and the workflow gives clear steps, but there's no executable code for creating the directory or files. The guidance is specific about format but lacks copy-paste-ready commands (e.g., `mkdir -p .learnings && touch .learnings/LEARNINGS.md`). The ID scheme (YYYYMMDD-XXX) doesn't explain how to generate the sequential XXX portion.

2 / 3

Workflow Clarity

The 4-step workflow is listed but lacks validation checkpoints. There's no guidance on how to verify an entry was logged correctly, no feedback loop for reviewing whether logged learnings are actually useful over time, and the promotion workflow lacks explicit validation steps before modifying shared guidance.

2 / 3

Progressive Disclosure

The content is well-structured with clear sections and headers, but the three full record-type templates inline make the file long. These templates could be split into separate reference files (e.g., TEMPLATES.md) with the SKILL.md providing a brief overview and link. No bundle files exist to support this split, and no external references are provided.

2 / 3

Total

8

/

12

Passed

Description

89%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

This is a strong description with excellent completeness and trigger term quality. The 'Use when' clause is particularly well-crafted with six specific, natural scenarios that make it easy for Claude to know when to select this skill. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., where learnings are stored, what format they take).

Suggestions

Add more specific concrete actions to the 'what' portion, e.g., 'Logs errors to a learnings file, records user corrections, and indexes solutions for future reference' instead of the more abstract 'captures learnings, errors, and corrections'.

DimensionReasoningScore

Specificity

The description names the domain (learnings, errors, corrections) and the general action (captures, enables continuous improvement), but the specific concrete actions are somewhat vague — 'captures learnings' and 'review learnings' are not as concrete as listing specific operations like 'logs error messages to a file' or 'updates a knowledge base with corrections'.

2 / 3

Completeness

Clearly answers both 'what' (captures learnings, errors, and corrections for continuous improvement) and 'when' with an explicit, detailed 'Use when' clause listing six specific trigger scenarios plus an additional instruction to review learnings before major tasks.

3 / 3

Trigger Term Quality

Excellent coverage of natural trigger phrases users would actually say: 'No, that's wrong...', 'Actually...', 'command fails', 'API fails', 'better approach', 'outdated', 'incorrect'. These are realistic conversational patterns that map well to when this skill should activate.

3 / 3

Distinctiveness Conflict Risk

This skill occupies a clear niche — meta-learning and error correction — that is unlikely to conflict with task-specific skills. The trigger scenarios are distinctive (user corrections, failed operations, outdated knowledge) and wouldn't overlap with typical domain-specific skills.

3 / 3

Total

11

/

12

Passed

Validation

90%

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

Validation10 / 11 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

10

/

11

Passed

Repository
jdrhyne/agent-skills
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.