CtrlK
BlogDocsLog inGet started
Tessl Logo

fastclaw-skill-guide

Create new skills for FastClaw agents. Use when the user asks to create a skill, turn a workflow into a skill, or build reusable automation. Also use when discussing skill format, structure, or best practices.

68

Quality

81%

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

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, actionable guide that respects token budget and gives a clear creation workflow with a verification step. The main room for improvement is adding an explicit error-recovery loop and splitting the long inline example into a reference file.

Suggestions

Add an explicit feedback loop to the Creation Steps (e.g., 'If load_skill fails to load, check frontmatter YAML syntax and fix before re-verifying') to reach the top workflow_clarity anchor.

Move the full PR-review example SKILL.md into a references/ file and link to it, keeping only a minimal skeleton inline to improve progressive disclosure.

Tighten the 'Writing the Description' Bad/Good example and the frontmatter table to remove minor verbosity and push conciseness toward the lean anchor.

DimensionReasoningScore

Conciseness

The guide is efficient with tables, code blocks, and lists and avoids explaining concepts Claude already knows, though the full inline PR-review example and the bad/good description pair could be trimmed slightly.

4 / 5

Actionability

Provides concrete, mostly executable guidance — exact directory layout, a frontmatter field table, storage paths like {agentDir}/skills/, a {baseDir} token, and a copy-paste example SKILL.md — with minor gaps such as the verify step only saying 'Use load_skill tool'.

4 / 5

Workflow Clarity

The 'Creation Steps' give a clear five-step sequence ending in a verify checkpoint ('Use load_skill tool to confirm it loads correctly'), but lack an explicit error-recovery feedback loop, so it falls short of the top anchor.

4 / 5

Progressive Disclosure

Well-organized into clear sections explaining the three-level loading model and when to move detail to references/, but with no bundle files present and the full example inlined, it has minor organization gaps rather than the well-signaled external references of the top anchor.

4 / 5

Total

16

/

20

Passed

Description

87%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 description that clearly states the skill's purpose and gives multiple explicit trigger contexts. It is specific, distinct, and complete with concrete 'Use when...' guidance.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions — 'Create new skills', 'turn a workflow into a skill', 'build reusable automation' — with only minor gaps (no mention of editing or debugging existing skills), fitting between the 1-2 action and comprehensive anchors.

4 / 5

Completeness

Explicitly answers both what ('Create new skills for FastClaw agents') and when ('Use when the user asks to create a skill... Also use when discussing skill format, structure, or best practices') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Covers natural phrases a user would say ('asks to create a skill', 'turn a workflow into a skill', 'skill format, structure, or best practices') but misses a few synonyms like 'make a skill' or 'skill template', so it sits just below the comprehensive anchor.

4 / 5

Distinctiveness Conflict Risk

Targets a clear niche — FastClaw skill authoring — with distinct, specific triggers and minimal overlap risk with unrelated skills.

5 / 5

Total

18

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

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.