CtrlK
BlogDocsLog inGet started
Tessl Logo

my-custom-skill

Example custom agent skill — a template to get started.

42

Quality

42%

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

Quality

Content

85%

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

The body is a well-organized, actionable template that clearly demonstrates the two skill patterns and a worked example. Its main weakness is residual template framing that slightly reduces conciseness.

DimensionReasoningScore

Conciseness

The body is mostly lean and avoids generic Claude-known concepts, but template scaffolding like "Behavioral Guidelines (Edit for Your Skill)" and "This is a template" adds framing that could be tightened, matching the score-2 anchor.

2 / 3

Actionability

It gives concrete, executable guidance — specific tool calls (ask_env, read, write, append, execute_skill_script, finish) and a worked journal example with a real path (journal.jsonl) — matching the score-3 anchor for actionable instruction-only guidance.

3 / 3

Workflow Clarity

The Daily Journal example lays out a clear four-step sequence (ask_env → read → append → finish); per the simple-skill scoring note, a single-purpose skill with an unambiguous sequence scores 3.

3 / 3

Progressive Disclosure

The skill is under 50 lines with no need for external references and is organized into clearly labeled sections (How Skills Work, Behavioral Guidelines, Example), satisfying the simple-skill exception for a score of 3.

3 / 3

Total

11

/

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.

The description is a placeholder that conveys no concrete capability, no user-facing trigger terms, and no usage guidance. It fails on every dimension because it describes a template rather than a usable skill.

Suggestions

Replace the generic phrasing with the specific concrete actions the skill performs (e.g., 'Creates and updates a daily journal from recent environment events').

Add an explicit 'Use when...' clause naming natural trigger terms a user would say (e.g., 'Use when the user asks to log the day, keep a journal, or record recent activity').

Use third-person action verbs that distinguish this skill from others to reduce conflict risk.

DimensionReasoningScore

Specificity

The phrase "a template to get started" names no concrete actions or capabilities, only an abstract purpose — matching the score-1 anchor "Vague or no actions; abstract language".

1 / 3

Completeness

It weakly implies "what" (a template) but entirely omits any "when to use" / "Use when..." clause, so both halves are not satisfied — capped below 2 per the missing-trigger guideline.

1 / 3

Trigger Term Quality

Terms like "custom agent skill" and "template" are not natural keywords a user would say when they need this skill; there are no recognizable trigger terms, matching the score-1 anchor.

1 / 3

Distinctiveness Conflict Risk

"Example custom agent skill — a template to get started" is maximally generic and would overlap with virtually any other skill, matching the score-1 anchor.

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
tsinghua-fib-lab/AgentSociety
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.