CtrlK
BlogDocsLog inGet started
Tessl Logo

my-custom-skill

Example custom agent skill — a template to get started.

33

Quality

28%

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 ./agentsociety/packages/agentsociety2/agentsociety2/custom/skills/examples/my-custom-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

57%

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-structured template that explains the two skill patterns and gives a concrete example workflow, with good progressive disclosure and a real referenced script. Its weaknesses are conceptual padding, placeholder rather than fully executable guidance, and missing validation checkpoints.

Suggestions

Trim architectural exposition (what skills are, how the extension mechanism works) down to the minimum a skill author needs, trusting Claude's existing knowledge.

Replace the 'Edit for Your Skill' placeholder steps with at least one complete, copy-paste-ready executable example.

For any multi-step workflow involving writes or batch operations, add an explicit validation/checkpoint step so the sequence earns a higher workflow-clarity score.

DimensionReasoningScore

Conciseness

The body is reasonably organized but spends tokens explaining architecture concepts Claude already knows ('the primary extension mechanism — like Claude Code's slash commands', 'Scripts cannot access the LLM or environment router'), so it is mostly efficient with some unnecessary explanation rather than lean.

2 / 3

Actionability

The journal example gives concrete step-level guidance ('workspace_read path journal.jsonl', 'codegen with instruction: ...') but the behavioral guidelines are placeholders labeled 'Edit for Your Skill' with no copy-paste-ready executable code, matching 'Some concrete guidance but incomplete'.

2 / 3

Workflow Clarity

A clear sequence is present (codegen → workspace_read → workspace_write → done), but there are no validation checkpoints or error-recovery loops, matching the score-2 anchor 'Steps listed but validation gaps'.

2 / 3

Progressive Disclosure

The body is under 50 lines with well-organized sections and a clearly signaled, one-level-deep reference to the real bundle file scripts/my-custom-skill.py, satisfying the simple-skill allowance for a top score.

3 / 3

Total

9

/

12

Passed

Description

0%

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 starter-template description rather than a real skill description: it states no capabilities, no trigger conditions, and no distinguishing niche. It scores the floor on every dimension.

Suggestions

Replace the template description with the concrete actions the actual skill performs (e.g., 'Extract text and tables from PDF files, fill forms, merge documents').

Add an explicit 'Use when...' clause naming natural user triggers so both the 'what' and 'when' are answered.

Use third-person action verbs and domain-specific keywords to distinguish the skill from other capabilities and reduce conflict risk.

DimensionReasoningScore

Specificity

The description 'Example custom agent skill — a template to get started.' names no concrete actions at all, only abstract template language, matching the score-1 anchor 'Vague or no actions; abstract language'.

1 / 3

Completeness

The description answers neither what the skill does nor when it should be used, and lacks any 'Use when...' clause, capping completeness at 1 per the missing-trigger guideline.

1 / 3

Trigger Term Quality

Neither 'custom agent skill' nor 'template to get started' are terms a user would naturally say when needing this skill, so there is effectively no usable trigger vocabulary.

1 / 3

Distinctiveness Conflict Risk

The wording is maximally generic and would overlap with essentially every other skill, matching the score-1 anchor 'Very generic; would conflict with many skills'.

1 / 3

Total

4

/

12

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

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

15

/

16

Passed

Repository
XiaoLuoLYG/GOD
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.