CtrlK
BlogDocsLog inGet started
Tessl Logo

skill-creation-walkthrough

Step-by-step guide for creating your own Claude Skills, from deciding whether a skill is the right tool to writing the SKILL.md file, structuring reference material, and making it trigger reliably. Use when you want to package a workflow, framework, or repeated task into a reusable Skill, when an existing skill is not triggering or not loading the right context, when you are auditing a skill that is underperforming, or when you want to publish a skill for others. Also triggers when someone asks "how do I make a skill" or "what makes a good skill". Useful for individuals, teams, and anyone publishing skills publicly.

81

1.24x
Quality

85%

Does it follow best practices?

Impact

98%

1.24x

Average score across 2 eval scenarios

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

77%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.

A well-structured, actionable meta-skill with clear sequencing, validation checkpoints, and properly signaled references. The main weakness is redundancy between the description deep-dive and Phase 3, which inflates length.

Suggestions

Collapse the "Deep dive: description anatomy" section into Phase 3 or move it into references/description-cookbook.md to remove redundancy and trim the body.

Move the worked post-mortem example into a reference file (e.g. references/example-skill-walkthrough.md) and summarize it in one line, keeping the body under the 250-line target the skill itself prescribes.

Tighten the "Bad/Good" description pairs in Phase 3 to a single compact comparison rather than four separate annotated sentences.

DimensionReasoningScore

Conciseness

Mostly efficient and well-organized, but the "Deep dive: description anatomy" section re-expands content already covered in Phase 3, and the worked example adds length that could be tightened or moved to a reference.

3 / 5

Actionability

Provides concrete, copy-paste-ready artifacts: the SKILL.md structure template, the 4-part description formula, a worked post-mortem example, and a defined output format; minor gaps remain in purely abstract framing at a few points.

4 / 5

Workflow Clarity

Six clearly sequenced phases with a testing checklist containing explicit validation checkpoints (trigger, edge-case, false-positive, output, length) and iteration feedback loops mapping symptoms to fixes.

5 / 5

Progressive Disclosure

Body is an overview with three real, one-level-deep reference files, all listed and described in the "Reference files" section with working relative links.

5 / 5

Total

17

/

20

Passed

Description

92%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 strong, third-person description that answers what and when with concrete trigger phrases and audience scoping. Minor synonym coverage gaps in trigger terms prevent a perfect trigger_term_quality score.

DimensionReasoningScore

Specificity

Lists multiple concrete actions—"deciding whether a skill is the right tool", "writing the SKILL.md file", "structuring reference material", and "making it trigger reliably"—covering the skill-creation workflow comprehensively.

5 / 5

Completeness

Explicitly answers both what it does (creating Claude Skills across the full lifecycle) and when to use it via concrete "Use when..." and "Also triggers when..." clauses.

5 / 5

Trigger Term Quality

Includes natural phrases users say ("how do I make a skill", "what makes a good skill", "publish a skill for others", "auditing a skill that is underperforming"), but a few common synonyms (e.g. "skill not working", "skill not loading") are only partially covered.

4 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (meta-skill for authoring/auditing skills) with distinct triggers unlikely to fire for unrelated skills.

5 / 5

Total

19

/

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.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

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

Warning

referenced_paths_exist

Referenced path issues: 1 missing

Warning

Total

14

/

16

Passed

Repository
rampstackco/claude-skills
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.