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User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task.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

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

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

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.

A well-structured, mostly lean instruction skill with concrete copy-paste templates, a clear workflow, and useful safety boundaries. It is uniformly strong rather than exceptional, with minor room to tighten overlap and make validation checkpoints inline.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence, using concrete templates and brief sections without explaining basic concepts; a few lines like the intro and 'Use for corrections...' labels slightly overlap the description and templates and could be trimmed.

4 / 5

Actionability

Copy-paste-ready markdown templates with exact fields (Logged, Priority, Status, Area) and concrete storage paths give mostly executable guidance; minor gaps remain in how the XXX sequence and ISO-8601 placeholders are to be filled.

4 / 5

Workflow Clarity

A clear four-step workflow is present, and Safety Boundaries supply validation gates ('Do not mark an entry resolved unless the fix was actually verified'), though checkpoints live outside the workflow steps rather than inline.

4 / 5

Progressive Disclosure

Well-organized sections (When to Use, Storage, Record Types, Workflow, Promotion Rules, Safety Boundaries) with content appropriately placed; no external references are used, which is acceptable for this self-contained skill but keeps it just below the clean one-level-deep reference ideal.

4 / 5

Total

16

/

20

Passed

Description

78%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, explicit description that clearly answers both what and when with six concrete trigger scenarios. It is held back only by slightly thin action specificity and a couple of broad triggers that could overlap with troubleshooting skills.

DimensionReasoningScore

Specificity

Names the domain ('learnings, errors, and corrections') with one concrete action ('Captures'), but does not enumerate the full set of record types or distinct actions the skill supports, leaving coverage incomplete.

3 / 5

Completeness

Explicitly states what it does ('Captures learnings, errors, and corrections to enable continuous improvement') and provides six concrete 'Use when' triggers plus a 'review learnings before major tasks' prompt, clearly answering both what and when.

5 / 5

Trigger Term Quality

Six numbered trigger scenarios use natural situations users encounter ('fails unexpectedly', 'No, that's wrong...', 'capability that doesn't exist'), giving good natural-term coverage, though the phrasing is scenario-based rather than keyword-based.

4 / 5

Distinctiveness Conflict Risk

The self-improvement / learning-capture niche is mostly distinct, though broad triggers like 'a command or operation fails unexpectedly' and 'an external API or tool fails' carry minor overlap risk with debugging skills.

4 / 5

Total

16

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

Total

15

/

16

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.