CtrlK
BlogDocsLog inGet started
Tessl Logo

common-workflow-writing

Rules for writing concise, token-efficient workflow and skill files. Prevents over-building that requires costly optimization passes. Use when creating or editing workflow files, SKILL.md files, or new skill definitions.

70

Quality

Does it follow best practices?

Impact

No eval scenarios have been run

SecuritybySnyk

Passed

No known issues

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.

A well-structured, token-efficient writing standard that models its own conciseness rules and includes a clear structure and pre-save checklist. Its main weakness is several broken/ambiguous sentences in the rules and self-check that reduce executable clarity.

Suggestions

Fix broken sentences: 'they one step' → 'merge them into one step'; 'every table row real structure' → 'is every table row real structure'; 'there any paragraphs bullet list could replace?' → 'are there paragraphs a bullet list could replace?'.

Make the 'Workflow Structure (Required order)' example slightly more concrete by showing what a one-sentence Goal and an imperative-verb Step look like, so the abstract numbered template is unambiguous.

DimensionReasoningScore

Conciseness

The body is lean and rule-driven — short bullets, a compact size-limits table, and an explicit 'No prose explanations' rule — practicing the token-efficiency it preaches and assuming Claude's competence.

3 / 3

Actionability

It gives concrete rules with delete-examples and numeric limits, but several instructions are grammatically broken and ambiguous ('they one step', 'every table row real structure', 'there any paragraphs bullet list could replace?'), leaving key guidance incomplete.

2 / 3

Workflow Clarity

The 'Workflow Structure (Required order)' gives a clear sequence and the 'Quick Self-Check Before Saving' checklist acts as an explicit validation checkpoint before output, which fits a single-purpose writing-standard skill.

3 / 3

Progressive Disclosure

At under 50 lines with well-organized sections (Core Rules, Size Limits, Workflow Structure, Anti-Patterns, Self-Check) and inline guidance to extract overflow to references/, the skill is appropriately self-contained per the simple-skill scoring note.

3 / 3

Total

11

/

12

Passed

Description

90%

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, third-person description that clearly states both capability and triggers with good natural-language keywords. Its only weakness is that the stated actions are abstract ('rules', 'prevents') rather than enumerating concrete operations.

Suggestions

Replace abstract phrasing like 'Rules for writing' and 'Prevents over-building' with concrete verbs the skill performs, e.g. 'Reviews, trims, and restructures workflow and SKILL.md files to enforce token-efficiency limits.'

DimensionReasoningScore

Specificity

Names the domain ('workflow and skill files') and some actions ('writing concise, token-efficient...', 'Prevents over-building'), but the actions are abstract rules rather than a list of multiple concrete operations, so it falls short of the level-3 anchor.

2 / 3

Completeness

It explicitly answers both what ('Rules for writing concise, token-efficient workflow and skill files') and when ('Use when creating or editing workflow files, SKILL.md files, or new skill definitions'), matching the level-3 anchor.

3 / 3

Trigger Term Quality

'Use when creating or editing workflow files, SKILL.md files, or new skill definitions' plus metadata keywords ('create workflow', 'write workflow', 'new skill', 'new workflow') give good coverage of natural terms a user would say.

3 / 3

Distinctiveness Conflict Risk

The niche is clearly defined (writing/optimizing workflow and SKILL.md files) with distinct file-path and keyword triggers, making it unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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
HoangNguyen0403/agent-skills-standard
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.