CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

update-skill

Create or update skills by generating, editing, or refining SKILL.md files in this repository. Use when authoring new skills or revising the structure, frontmatter, or guidance for existing ones.

Quality

82%

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

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 is a well-organized, largely actionable authoring guide with a concrete quick-start example, specific requirements, a validation command, and correctly-linked one-level-deep references. Its main weaknesses are redundancy — overlapping 'File Organization'/'When to Split Content' sections and inlined description examples that duplicate the references file — and an optional validation step without any error-recovery guidance.

Suggestions

Merge 'File Organization' and 'When to Split Content' into a single section — both restate the same <=200-lines / references/ splitting rule.

Condense 'Writing Effective Descriptions' to a two-line rule plus a pointer to 'Description Best Practices' in references/best-practices.md, moving the full example descriptions into that reference file.

Promote the skills-ref validation step from 'Optionally' to a required final step in the authoring workflow, with a short fix-and-revalidate loop when validation fails.

DimensionReasoningScore

Conciseness

Mostly efficient but includes unnecessary duplication: 'File Organization' and 'When to Split Content' both restate the same 200-line/references/ rule, and 'Writing Effective Descriptions' inlines two full example descriptions plus a vague-description warning that overlaps 'Description Best Practices' in references/best-practices.md. This fits the 'mostly efficient but includes some unnecessary explanation or could be tightened' anchor rather than the 4 anchor's 'minor instances'.

3 / 5

Actionability

Provides a complete worked SKILL.md example, concrete frontmatter rules with examples ('add-feature-flag', 'pdf-processing'), a copy-paste validation command ('skills-ref validate ./my-skill'), line-count thresholds, and real example paths — matching 'mostly executable guidance; concrete code or commands with minor gaps'. The vague 'If not installed, use the WebSearch tool to get context around this package' keeps it below the fully-executable 5 anchor.

4 / 5

Workflow Clarity

The guidance follows a sensible progression (quick-start template → frontmatter requirements → structure → validation → content organization), and a validation checkpoint with a concrete command is present, fitting 'clear sequence with most checkpoints present; minor validation gaps'. It does not reach 5 because validation is labeled 'Optionally' with no error-recovery or fix-and-retry loop, and the sequence is implied by topic order rather than explicitly numbered.

4 / 5

Progressive Disclosure

references/best-practices.md is one level deep, referenced with clear markdown links that name the exact sections to read ('Description Best Practices', 'Conciseness Principles', 'Code Example Formatting'), and all referenced sections exist — good structure with mostly appropriate placement. It falls short of the 5 anchor because some detailed content (description-writing examples and best-practice summaries) is inlined in SKILL.md where the split guidance would place it in the reference file.

4 / 5

Total

15

/

20

Passed

Description

87%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 description that explicitly states what the skill does and when to use it, with concrete action verbs and an explicit 'Use when...' trigger clause in appropriate third-person voice. Keyword coverage is good, though a few natural synonyms ('write', 'edit' a skill) are absent and the action list could be more comprehensive.

DimensionReasoningScore

Specificity

Names the target artifact and three concrete actions — 'generating, editing, or refining SKILL.md files' — which matches the 'several specific actions; minor gaps' anchor. It falls short of the 5 anchor because coverage omits related actions like validating or splitting skill content.

4 / 5

Completeness

Explicitly answers both parts: the 'what' is 'Create or update skills by generating, editing, or refining SKILL.md files' and the 'when' is a concrete 'Use when authoring new skills or revising the structure, frontmatter, or guidance for existing ones' clause. This directly matches the 5 anchor's clear what-and-when with concrete trigger phrases.

5 / 5

Trigger Term Quality

Contains good natural keywords users would actually say — 'Create or update skills', 'authoring new skills', 'SKILL.md', 'frontmatter', 'structure' — matching 'good keyword coverage; a few natural terms missing'. Missing synonyms such as 'write', 'edit', or 'skill file' keep it below the comprehensive 5 anchor.

4 / 5

Distinctiveness Conflict Risk

The triggers 'SKILL.md files', 'frontmatter', and 'authoring new skills' carve out a clear niche with minimal overlap with other skills, matching the 'clear niche with distinct triggers' anchor. It is above the 4 anchor because the domain-specific trigger terms are unlikely to fire for unrelated documentation or coding requests.

5 / 5

Total

18

/

20

Passed

Validation

100%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

warpdotdev/common-skills

Path

.agents/skills/update-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.