skill-authoring

Principles for writing skills that behave the same way every run — use when adding, editing, or reviewing a skill in this plugin

Quality

68%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/skill-authoring/SKILL.md

Quality

Content

75%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-structured, actionable instruction skill with a clear workflow shape, an explicit output contract, and verification checkpoints. It is concise and uses one-level-deep references well, though some referenced files are absent from the bundle and a little inline guidance could be pushed further down.

Dimension	Reasoning	Score
Conciseness	The body is lean instructional prose organized under clear headers and largely assumes Claude's competence; minor over-explanation remains in the opening Codex host-adapter blockquote and the 'determinism out of a stochastic system' thesis, keeping it just below the fully lean anchor.	4 / 5
Actionability	As an instruction-only skill it gives concrete, specific guidance — 'Lead with the word that does the invoking', 'One trigger per branch', a five-point Output Contract, and a checkable Verification list — with only minor gaps versus copy-paste-ready precision.	4 / 5
Workflow Clarity	A clear sequence runs from When To Use → Inputs → Workflow → Output Contract → Verification, with the Verification section acting as explicit checkpoints; it is principle-oriented rather than a rigid destructive workflow, so it stops short of the full feedback-loop anchor at 5.	4 / 5
Progressive Disclosure	Content is well-sectioned and pushes detail behind one-level-deep pointers (skills/blocks/*, docs/PLUGIN-ASSEMBLY-STANDARD.md), but the referenced files are not present in the bundle (references/scripts/assets absent) and a fair amount of guidance remains inline, so it does not fully reach the clean overview-plus-references anchor.	4 / 5
	Total	16 / 20 Passed

Description

62%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 answers both what and when with explicit, scoped trigger guidance, but its actions are generic verbs and it omits common synonym triggers. It is distinct within its plugin niche though it edges near sibling meta-skills.

Suggestions

Lead the description with the strongest natural trigger verb (e.g. 'Write, edit, or review skills...') to raise specificity and trigger term quality.

Add common synonyms a user would actually say — 'writing', 'creating', 'authoring', or 'reviewing a skill PR' — to broaden trigger coverage.

Tighten the 'what' clause to name the concrete deliverable (e.g. 'principles and a review checklist for...') so completeness approaches the fully concrete anchor.

Dimension	Reasoning	Score
Specificity	Names the domain ('writing skills that behave the same way every run') and concrete actions ('adding, editing, or reviewing a skill'), but the verbs are generic and coverage is not comprehensive, matching the '1-2 concrete actions' anchor rather than the multi-action anchor above.	3 / 5
Completeness	It states a clear 'what' ('Principles for writing skills that behave the same way every run') and an explicit 'when' ('use when adding, editing, or reviewing a skill in this plugin'), but the 'what' is slightly abstract, so it does not reach the fully concrete trigger-phrase anchor at 5.	4 / 5
Trigger Term Quality	'adding, editing, or reviewing a skill' are natural phrases a user might say, but common variations and synonyms ('writing', 'creating', 'authoring', 'reviewing a PR') are missing, so it sits at 'some relevant keywords but missing synonyms' rather than 'good coverage'.	3 / 5
Distinctiveness Conflict Risk	Scoped to 'this plugin' and focused on the niche of skill authoring/review, giving it a clear niche with minimal conflict risk; minor overlap remains with closely related meta-skills (e.g. skill-meta-prompt referenced in the body).	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: nyldn/claude-octopus
Path: skills/skill-authoring/SKILL.md
Commit: 0093dab

Reviewed: 5 days 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.