CtrlK
BlogDocsLog inGet started
Tessl Logo

fastclaw-skill-learner

Analyze conversations to extract reusable skill patterns. Used internally by FastClaw to auto-generate skills from complex multi-step tasks.

56

Quality

64%

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 ./skills/fastclaw-skill-learner/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

78%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 a well-organized, concise instruction skill with clear decision criteria and concrete output formats. Its main gap is a fully worked example for the reusable-extraction case and the absence of feedback loops, though the latter is not strictly required here.

Suggestions

Add one fully filled-in reusable-extraction JSON example with a real (anonymized) skill name, slug, description, and a short content snippet so the output is copy-paste demonstrable.

Tighten the 'Example Extraction' section slightly; the prose narrative could be condensed into the concrete output format already shown.

DimensionReasoningScore

Conciseness

The body is efficient and assumes Claude's competence without explaining basic concepts; only minor phrasing could be trimmed, fitting the 'efficient, minor over-explanation' anchor.

4 / 5

Actionability

Concrete JSON output schemas and explicit decision criteria give mostly executable guidance, though the example output lacks a fully filled worked example for the reusable case.

4 / 5

Workflow Clarity

A clear sequence (extract criteria, analysis steps, output format, guidelines) with decision gates is present; it is not a destructive/batch operation so no validation cap applies, though error-recovery feedback loops are absent.

4 / 5

Progressive Disclosure

A single-file, well-sectioned instruction skill under ~70 lines with clear headers and no nested references qualifies for the simple-skill top score.

5 / 5

Total

17

/

20

Passed

Description

50%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 states what the skill does clearly enough but omits any explicit 'when to use' trigger guidance and mixes in internal-facing language. It sits at a middling level across specificity, triggers, and completeness.

Suggestions

Add an explicit 'Use when...' clause naming the natural situations a user would invoke this, e.g. 'Use when reviewing a multi-step conversation to capture a reusable skill.'

Replace internal jargon ('Used internally by FastClaw to auto-generate skills') with user-facing trigger terms like 'extracting skills from transcripts' or 'saving reusable workflows'.

List 1-2 more concrete actions (e.g. 'identifies repeatable step sequences and outputs a SKILL.md') to raise specificity beyond a single action.

DimensionReasoningScore

Specificity

Names the domain ('conversations') and one concrete action ('extract reusable skill patterns') but offers no broader coverage of actions, matching the 1-2 concrete actions anchor.

3 / 5

Completeness

It has a clear 'what' but no 'when'/'Use when...' trigger guidance, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Some relevant keywords ('conversations', 'skill patterns') appear, but the description lacks the natural user-facing trigger phrases and includes internal jargon ('Used internally by FastClaw').

3 / 5

Distinctiveness Conflict Risk

The niche (skill extraction from conversations) is fairly specific, but without explicit trigger phrases it could still overlap with other analysis skills.

3 / 5

Total

12

/

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

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

Total

14

/

16

Passed

Repository
fastclaw-ai/fastclaw
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.