CtrlK
BlogDocsLog inGet started
Tessl Logo

evidence-driven-writing

Use when writing or revising Introduction, Related Work, background, literature synthesis, or any section where references must drive claims

76

Quality

95%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%Weight 40%Scale 1-3

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

A well-structured instruction skill: lean, concrete templates, explicit gated workflow with checkpoints, and a single clearly signaled reference file. It assumes competence and adds only what Claude would not already know.

DimensionReasoningScore

Conciseness

The body is lean and assumes Claude's competence — it never explains what an Introduction or GPR is — and every section (Hard Gate, Evidence Map, Blueprint, patterns, gates, sample pointer) earns its place, matching the 3-anchor.

3 / 3

Actionability

It supplies concrete, copy-paste-ready templates — an evidence-map table with exact columns and a paragraph blueprint with explicit fields — which is concrete specific guidance for an instruction-only skill, satisfying the 3-anchor without needing code.

3 / 3

Workflow Clarity

The process is explicitly sequenced with validation checkpoints: a Hard Gate listing required artifacts, 'Only after the blueprint is complete may manuscript prose be written,' plus the Anti-Enumeration Gate and Body Contamination Firewall acting as review criteria, matching the 3-anchor for clear sequencing with explicit checkpoints.

3 / 3

Progressive Disclosure

The body is an overview that signals a single one-level-deep reference to the real file 'references/gpr-introduction-example.md' with clear usage guidance, matching the 3-anchor for a clear overview with well-signaled one-level references.

3 / 3

Total

12

/

12

Passed

Description

90%Weight 40%Scale 1-3

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 concise, well-structured description with an explicit 'Use when' trigger and natural section-name keywords; its only weakness is a thin action vocabulary (writing/revising) rather than a richer set of concrete actions.

DimensionReasoningScore

Specificity

The phrase 'writing or revising Introduction, Related Work, background, literature synthesis' names the domain and a couple of actions, but the action vocabulary is limited to 'writing or revising' rather than a list of multiple distinct concrete actions as the 3-anchor requires.

2 / 3

Completeness

It explicitly answers both 'what' (writing/revising citation-driven sections) and 'when' via the explicit 'Use when writing or revising ...' clause, matching the 3-anchor that requires both with an explicit trigger.

3 / 3

Trigger Term Quality

Natural section names a user would actually say ('Introduction', 'Related Work', 'background', 'literature synthesis') are well covered, matching the 3-anchor's expectation of good coverage of natural terms.

3 / 3

Distinctiveness Conflict Risk

The niche is clearly bounded to evidence/reference-driven manuscript sections, with triggers unlikely to fire for unrelated skills, matching the 3-anchor for a clear distinct niche.

3 / 3

Total

11

/

12

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
Norman-bury/research-writing-skill
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.