open-knowledge-write-skill

Use when the user wants to create, author, write, or design a new Agent Skill (a SKILL.md) — for OpenKnowledge or for their editors — including requests like 'help me write a skill', 'make a skill that…', 'turn this workflow into a skill', or improving an existing skill's triggering and discipline. Also use when capturing reusable agent guidance that should live as an installable skill rather than a one-off prompt. Covers choosing scope (project vs global), authoring inside a plugin or skills-distribution repo (write in the repo's own layout, never install), the SKILL.md frontmatter contract, progressive-disclosure structure, evaluating the skill, and installing it into the user's editors.

Quality

91%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

92%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-engineered, mostly lean skill body with executable verb-call examples, a clear staged workflow, validation gates, and a RED/GREEN feedback loop, plus correctly structured one-level-deep references. The only meaningful weakness is localized duplication of the reference-path and scope/install guidance across stages and the Reminders section.

Suggestions

State the reference-path convention (backtick vs wiki-link, project vs global, one level deep) once — e.g. in Stage 3 — and have Stage 5 simply reference it, removing the near-verbatim repeat.

Trim the Reminders section so it does not re-explain scope/install mechanics already covered in Stages 2 and 8; keep only the cross-cutting cautions not stated earlier.

Dimension	Reasoning	Score
Conciseness	Mostly lean and imperative with no padding of concepts Claude already knows, but the reference-path guidance (backtick vs wiki-link, global vs project, one level deep) is restated nearly verbatim in both Stage 3 and Stage 5, and the Reminders section re-iterates scope/install points already covered in the stages — minor instances that could be trimmed.	4 / 5
Actionability	Fully executable guidance: concrete copy-pasteable code blocks for write/edit/skills/delete/install with real parameter shapes, an exact scope table, and the precise frontmatter contract (name rules, ≤1024 chars, no XML tags).	5 / 5
Workflow Clarity	Stages 1–8 are an explicit ordered sequence with validation checkpoints: the Stage 1 disclosure gate ('Check BEFORE you build') and the Stage 4 RED → Stage 6 GREEN → pressure-test → patch-and-re-test loop provide clear feedback loops for error recovery.	5 / 5
Progressive Disclosure	The body is an overview that points to two real, one-level-deep reference files — references/description-optimization.md (Stage 7) and references/pressure-testing.md (Stage 6) — both present in ./references/ and clearly signaled in context; depth is appropriately split out.	5 / 5
	Total	19 / 20 Passed

Description

91%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, trigger-first description that leads with 'Use when', enumerates concrete user phrasings, and disambiguates installable-skill authoring from one-off prompts. The only weakness is that the 'Covers...' tail reads as a topic list rather than crisp actions, and one clause is slightly broad.

Suggestions

Tighten the 'Covers choosing scope... progressive-disclosure structure... evaluating the skill...' tail into concrete verbs (e.g. 'pick project vs global scope', 'structure the body with progressive disclosure', 'pressure-test the skill') to lift specificity toward 5.

Narrow 'capturing reusable agent guidance' to a phrasing that cannot be mistaken for general prompt-writing, e.g. 'capturing reusable agent guidance as an installable SKILL.md', to reduce overlap risk with adjacent skills.

Dimension	Reasoning	Score
Specificity	Names several concrete actions ('create, author, write, or design a new Agent Skill', 'choosing scope', 'evaluating the skill', 'installing it'), but the 'Covers choosing scope... progressive-disclosure structure... evaluating...' clause is more a topic enumeration than fully concrete verbs, leaving minor gaps versus a comprehensive action list.	4 / 5
Completeness	Explicitly answers both: the 'when' via 'Use when the user wants to... including requests like...' with concrete trigger phrases, and the 'what' via 'Covers choosing scope... the SKILL.md frontmatter contract... installing it into the user's editors.'	5 / 5
Trigger Term Quality	Comprehensive natural trigger phrasings quoted verbatim — "'help me write a skill'", "'make a skill that…'", "'turn this workflow into a skill'" — plus 'improving an existing skill's triggering and discipline', covering the phrases a user would actually type.	5 / 5
Distinctiveness Conflict Risk	Clear niche (authoring an Agent Skill / SKILL.md for OpenKnowledge) with distinctive quoted triggers, but the clause 'capturing reusable agent guidance that should live as an installable skill rather than a one-off prompt' is slightly broad and risks minor overlap with adjacent prompt-/knowledge-management skills.	4 / 5
	Total	18 / 20 Passed

Validation

81%

Warnings & errors only

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

Validation — 13 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
relative_links	Relative link issues: 1 missing	Warning
referenced_paths_exist	Referenced path issues: 4 missing	Warning

	Total	13 / 16 Passed

Repository: inkeep/open-knowledge
Path: packages/server/assets/skills/write-skill/SKILL.md
Commit: 60997a2

Reviewed: 1 day ago

Table of Contents

Discovery Implementation Validation

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.