CtrlK
BlogDocsLog inGet started
Tessl Logo

writing-fragments

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

58

Quality

66%

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

Fix and improve this skill with Tessl

tessl review fix ./skills/in-progress/writing-fragments/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

88%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 lean, well-structured instruction-only skill with concrete guidance and a clear, checkpointed append-only workflow. It earns top marks for conciseness, workflow clarity, and organization, with only minor actionability room around edge-case handling.

DimensionReasoningScore

Conciseness

Lean and efficient throughout; assumes Claude's competence, never explains what markdown or writing is, and every line earns its place.

5 / 5

Actionability

Provides concrete executable guidance ('append to a single markdown file', 'single H1 at the top', 'separated by a horizontal rule') and a copy-paste file-format example, with only minor gaps in coverage of edge cases.

4 / 5

Workflow Clarity

Clear sequence (ask path once -> capture from first turn -> H1 on first write -> append silently -> re-read before every write -> handle cut/rewrite/merge) with the re-read-before-write step acting as an explicit validation checkpoint against clobbering user edits.

5 / 5

Progressive Disclosure

A simple single-purpose skill under ~60 body lines with no need for external references; its three well-organized sections (What is a fragment / File format / Writing rhythm) make navigation easy, qualifying for the simple-skill 5.

5 / 5

Total

19

/

20

Passed

Description

43%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 is concise and names a clear niche (writing explore vs exploit) but is too terse to comprehensively convey capabilities or trigger terms, and lacks an explicit 'Use when' clause. Strengthening it with concrete actions and natural trigger phrases would lift specificity and completeness.

Suggestions

Add 1-2 concrete actions to the description, e.g. 'Run a grilling interview that surfaces raw fragments and append them to a single markdown file.'

Append an explicit trigger clause, e.g. 'Use when the user wants to brainstorm or explore raw writing material before committing to structure or an outline.'

Include natural synonyms users would say ('draft', 'brainstorm', 'gather material') to broaden trigger term coverage.

DimensionReasoningScore

Specificity

Names the writing/explore domain and one metaphorical action ('mine raw fragments') but the actions are minimal and not comprehensive, sitting just below the 1-2 concrete actions anchor.

2 / 5

Completeness

Has a clear 'what' (mine raw fragments in explore) but lacks an explicit 'Use when...' trigger clause, with 'when' only weakly implied by 'explore'; per guidelines missing trigger guidance caps completeness at 3.

3 / 5

Trigger Term Quality

Includes some relevant natural terms ('Writing', 'explore', 'fragments') but misses common variations users would actually say like 'draft', 'brainstorm', or 'outline ideas'.

3 / 5

Distinctiveness Conflict Risk

The 'explore vs exploit' niche is somewhat specific but the compact 'Writing, explore' phrasing could still overlap with general writing or drafting skills.

3 / 5

Total

11

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
mattpocock/skills
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.