writing-great-skills

Reference for writing and editing skills well — the vocabulary and principles that make a skill predictable. Reach for it when authoring, pruning, or debugging a skill.

Quality

63%

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/writing-great-skills/SKILL.md

Quality

Content

63%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-organized, vocabulary-driven reference that practices what it preaches on compression and information hierarchy, with clear actionable tests embedded in the prose. Its main defect is that GLOSSARY.md — the single external reference the whole skill leans on — is missing from the bundle.

Suggestions

Add the missing GLOSSARY.md file so the bold-term pointers resolve; without it the skill's core progressive-disclosure move is a dead link.

Include one or two worked before/after examples of an actual skill edit (e.g. collapsing a duplicated triad into a leading word) to lift actionability from conceptual to executable.

Tighten the longer prose passages in 'Information hierarchy' and 'Leading words' where the conceptual argument restates itself.

Dimension	Reasoning	Score
Conciseness	The body is dense, leverages leading words to compress restatements, and avoids explaining concepts Claude already knows; it earns a 4 with only minor passages of prose that could be tightened, stopping short of the lean 'every token earns its place' bar.	4 / 5
Actionability	It gives several concrete directives and tests ("run the no-op test on each sentence", "sharpen the completion criterion first", "delete the whole sentence rather than trim"), but the guidance is mostly conceptual prose without worked before/after examples of actual skill edits, leaving it at 'some concrete guidance but incomplete'.	3 / 5
Workflow Clarity	Sections are well-organized with ordered decision frameworks (the information-hierarchy ladder, the pruning order, and the "Defence, in order" sequence in Failure modes); not a 5 because there are no explicit validation checkpoints, though none are strictly required for a reference skill with no destructive or batch operations.	4 / 5
Progressive Disclosure	The body is well-sectioned and follows its own disclosure principle by pushing full term definitions behind a one-level pointer to GLOSSARY.md, but no GLOSSARY.md file exists in the skill folder, so the primary context pointer is a broken reference that breaks navigation — capping it at 'some structure but references not effectively delivered'.	3 / 5
	Total	14 / 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.

A solid, human-facing description (the skill is user-invoked via disable-model-invocation) that clearly pairs a 'what' with a 'when' and occupies a distinct niche. It loses points mainly for thin natural-keyword coverage in the trigger clause.

Suggestions

Add the natural phrasing users actually say (e.g. 'writing, editing, reviewing, or debugging a skill') to the trigger clause so common synonyms are covered.

Consider a 'Use when...' formulation with a couple of concrete trigger variants to lift completeness and trigger_term_quality from 3-4 toward 5.

Dimension	Reasoning	Score
Specificity	The description names the domain ("writing and editing skills well") and a few concrete actions ("authoring, pruning, or debugging"), but frames itself as a "Reference" rather than listing comprehensive capabilities, fitting the 'names domain and 1-2 concrete actions' anchor rather than the fuller coverage of a 4.	3 / 5
Completeness	It clearly states both what ("Reference for writing and editing skills well — the vocabulary and principles...") and when ("Reach for it when authoring, pruning, or debugging a skill"), with an explicit trigger clause; not a 5 only because the trigger phrasing is thinner than the multi-synonym 'Use when...' examples.	4 / 5
Trigger Term Quality	"Reach for it when authoring, pruning, or debugging a skill" offers relevant trigger verbs, but the natural phrasing users would say ("writing", "editing", "reviewing a skill") is largely absent from the trigger clause, leaving common synonyms missing per the anchor-3 example.	3 / 5
Distinctiveness Conflict Risk	The niche (skill authoring/pruning/debugging) is distinct with specific triggers and low conflict risk versus most skills; a 5 is not warranted because it could mildly overlap with general code-review or refactoring skills.	4 / 5
	Total	14 / 20 Passed

Validation

93%

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 — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 missing	Warning

	Total	15 / 16 Passed

Repository: tslateman/duet
Path: skills/writing-great-skills/SKILL.md
Commit: 5647baf

Reviewed: 3 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.