writing-fragments

Writing, explore — mine raw fragments, no structure yet.

Quality

—

Does it follow best practices?

Impact

—

No eval scenarios have been run

Securityby

Passed

No known issues

Quality

Content

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body delivers concrete, actionable guidance with a clear workflow and an explicit pre-write checkpoint, well-organized into a self-contained single-purpose document. Its only weakness is a few metaphorical passages that add tokens without adding instruction.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and defines genuinely novel concepts (fragments, leading word), but the 'novelist's diary' metaphor and the florid leading-word elaboration ('paying dividends through the entire exploit phase') could be tightened.	2 / 3
Actionability	As an instruction-only skill it gives concrete, specific guidance — H1 on first write, fragments separated by '\n---\n', no body headings — plus a copy-paste-ready file-format template, matching the top anchor.	3 / 3
Workflow Clarity	The first-write (H1) vs. append sequence is unambiguous, and the pre-write checkpoint of re-reading from disk to preserve user edits (never overwrite) is an explicit validation step for a fragile shared-file operation.	3 / 3
Progressive Disclosure	The skill is self-contained and single-purpose with no bundle files, organized into clear <what-to-do> and <supporting-info> subsections and no nested references, meeting the simple-skill top anchor.	3 / 3
	Total	11 / 12 Passed

Description

50%

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 is terse and gestures at a concrete action, but it lacks explicit trigger guidance and relies on skill-specific jargon ("fragments") rather than natural user terms. It is distinguishable from its exploit counterpart only loosely.

Suggestions

Add an explicit 'Use when…' clause naming natural triggers, e.g. 'Use when the user wants to brainstorm, freewrite, or explore raw material for an article before committing to structure.'

Replace or supplement the jargon term 'fragments' with natural keywords users would actually say (brainstorm, draft ideas, free writing, explore what to write).

Name a couple more concrete actions (interview the user, append each fragment to a single markdown file) to lift specificity toward the top anchor.

Dimension	Reasoning	Score
Specificity	It names the domain ("Writing") and a concrete action ("mine raw fragments"), but does not list multiple specific actions, matching the 'names domain and some actions, but not comprehensive' anchor.	2 / 3
Completeness	It conveys a weak 'what' ("mine raw fragments") but provides no 'Use when…' or equivalent trigger guidance for when to invoke the skill, capping completeness at 2.	2 / 3
Trigger Term Quality	"Writing" and "explore" are terms a user might say, but "fragments" is skill jargon and common variations like brainstorm, draft, or freewrite are absent, so coverage is partial.	2 / 3
Distinctiveness Conflict Risk	"no structure yet" distinguishes it from the paired exploit phase, but the leading word "Writing" is generic and could overlap with sibling writing skills.	2 / 3
	Total	8 / 12 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: mattpocock/skills
Commit: 66f92b6

Reviewed: 4 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.