CtrlK
BlogDocsLog inGet started
Tessl Logo

create-skill

Guide for creating effective skills. This skill should be used when users want to create a new skill (or update an existing skill) that extends your capabilities with specialized knowledge, workflows, or tool integrations.

64

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

73%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 a well-sequenced, actionable creation workflow with strong validation and iteration guidance, and it practices the progressive disclosure it preaches. Main weaknesses are the duplicated initialization example, inlined pattern examples, and two referenced files that cannot be verified in the bundle.

Suggestions

Replace the fully duplicated global-skill initialization block with a one-line note ("substitute {{global_skills_path}} for {{local_skills_path}}"), cutting ~40 redundant lines and tightening conciseness.

Ship references/workflows.md and references/output-patterns.md (or remove the pointers if they will not exist), so the body's design-pattern guidance resolves to real files and strengthens both actionability and progressive disclosure.

Move the three inline progressive-disclosure pattern examples (high-level guide, domain organization, conditional details) into a single reference file, keeping only the selection principle in SKILL.md to reduce context bloat.

DimensionReasoningScore

Conciseness

The ~40-line project-local initialization bash block is duplicated almost verbatim for the global-skill variant (differing only in the path variable), and the "Anatomy of a Skill" tree repeats structure details later restated in Step 3. The guidance itself is largely non-obvious and valuable, but these redundancies go beyond the "minor trims" allowed at anchor 4.

3 / 5

Actionability

Concrete, executable material is abundant (mkdir/pdftk bash snippets, sample user questions, good/bad naming pairs, a full description example), matching anchor 4. It falls short of 5 because the body directs readers to references/workflows.md and references/output-patterns.md which are not present in the bundle, and command paths use {{placeholders}} requiring substitution.

4 / 5

Workflow Clarity

The five-step creation process is clearly sequenced with explicit per-step skip conditions, an explicit validation requirement ("Added scripts must be tested by actually running them"), and a defined iterate feedback loop in Step 5. This matches anchor 5's clear sequence, validation steps, and feedback loop.

5 / 5

Progressive Disclosure

Sections are well organized, the body stays under its own 500-line guidance, and references are clearly signaled and one level deep ("See references/workflows.md for sequential workflows and conditional logic"). It falls short of 5 because the referenced files are absent from the provided bundle and the three progressive-disclosure pattern examples are inlined rather than split out, per anchor 4's "minor organization gaps".

4 / 5

Total

16

/

20

Passed

Description

82%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.

The description cleanly states what the skill does and gives an explicit, natural trigger clause for creating or updating skills. Trigger terms are good though not exhaustive of common synonyms. Distinctiveness is strong since skill creation is a well-defined niche.

DimensionReasoningScore

Specificity

"Guide for creating effective skills" names the domain with 1-2 concrete actions (creating/updating a skill), while "extends your capabilities with specialized knowledge, workflows, or tool integrations" describes the output artifact rather than adding more concrete actions. This matches anchor 3; it falls short of 4 because it does not list several specific actions.

3 / 5

Completeness

It explicitly answers both: what ("Guide for creating effective skills") and when ("This skill should be used when users want to create a new skill (or update an existing skill) that extends your capabilities..."). The when-clause is explicit with concrete trigger phrasing, matching anchor 5 rather than 4.

5 / 5

Trigger Term Quality

"create a new skill (or update an existing skill)" captures the natural phrases a user would say when needing this skill. It falls short of anchor 5 because common synonyms and variations (e.g., "write a skill", "author a skill", "build a skill", "skill template") are missing.

4 / 5

Distinctiveness Conflict Risk

Skill creation is a clear niche with distinct, unambiguous triggers; it would not plausibly fire for unrelated skills. The broad phrase "extends your capabilities with specialized knowledge" is tied to the skill-creation trigger, keeping conflict risk minimal.

5 / 5

Total

17

/

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

relative_links

Relative link issues: 6 missing

Warning

referenced_paths_exist

Referenced path issues: 14 missing

Warning

Total

14

/

16

Passed

Repository
tailcallhq/forgecode
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.