CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

write-skill

Use when creating a new skill, editing an existing skill, or verifying a skill works before deployment.

Quality

75%

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/write-skill/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 body delivers concrete, actionable guidance: a complete SKILL.md template, executable search/validation commands, and a well-sequenced TDD workflow with feedback loops. Its main weaknesses are redundant restatements of the same rules across sections and an abstract, non-executable RED baseline-testing procedure.

Suggestions

Consolidate the description rules stated three times (CSO section, template description guidance, Rules #3) into a single authoritative location to reduce token cost.

Make the RED baseline step executable: specify the exact command or procedure for running an agent without the skill (e.g., a concrete test harness invocation or scenario file format) instead of 'Ask an agent to handle it WITHOUT the skill loaded'.

Move the full SKILL.md template and/or validation checklist into a reference file (e.g., references/template.md) and link to it from the main body, keeping SKILL.md as a lean overview.

DimensionReasoningScore

Conciseness

Mostly efficient, but core rules are repeated three times across sections ('NEVER summarize the workflow' appears in CSO rules, the template description, and Rules #3; 'Use when...' likewise), and the Anti-Rationalization pattern appears both as a template stub and a full table, so it could be meaningfully tightened.

3 / 5

Actionability

Provides a copy-paste-ready SKILL.md template and concrete commands ('find skills/ -name "SKILL.md" | head -30', 'grep -l "[keyword]" skills/*/SKILL.md', 'node tests/validate-agents.mjs --strict'), but the RED baseline-testing step is described abstractly ('Ask an agent to handle it WITHOUT the skill loaded') with no executable procedure.

4 / 5

Workflow Clarity

The RED → GREEN → REFACTOR cycle is a clearly sequenced feedback loop with explicit re-testing ('Re-test until the skill is bulletproof') and a validation checklist, but the document presents structure/template before the TDD cycle that should govern it, and lacks recovery guidance for validation failures.

4 / 5

Progressive Disclosure

A single-file bundle with well-organized sections and no buried or nested references. The ~50-line template and long validation checklist could arguably live in separate reference files to keep the main body leaner, which keeps it short of a 5.

4 / 5

Total

15

/

20

Passed

Description

75%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 solid 'Use when...' description that follows its own CSO advice: trigger-focused, third person, concise. Its main limitation is that the 'what' is only implicit inside the trigger clause, and it lacks synonym coverage for common phrasings like 'write a skill' or 'test a skill'.

DimensionReasoningScore

Specificity

Names the domain (skills) and three concrete actions — 'creating a new skill, editing an existing skill, or verifying a skill works' — but leaves the actual capabilities (writing SKILL.md, optimizing descriptions, TDD testing) unstated, so coverage has minor gaps rather than being comprehensive.

4 / 5

Completeness

The explicit 'Use when...' clause clearly answers 'when', and the 'what' (create/edit/verify) is embedded in that clause, but the two are merged rather than stated separately with concrete trigger phrases, so it falls short of the anchor requiring both explicitly.

4 / 5

Trigger Term Quality

'creating a new skill', 'editing an existing skill', and 'verifying a skill works' are natural phrases a user would say, but common variations like 'write a skill', 'test a skill', or 'skill isn't working' are missing.

4 / 5

Distinctiveness Conflict Risk

Skill authoring is a clear, distinct niche, but 'verifying a skill works before deployment' has minor overlap risk with general testing/validation skills.

4 / 5

Total

16

/

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.

Validation — 14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

allowed_tools_field

'allowed-tools' contains unusual tool name(s)

Warning

frontmatter_unknown_keys

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

Warning

Total

14

/

16

Passed

Repository

fernandezbaptiste/specialist-agent

Path

skills/write-skill/SKILL.md

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.