CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

cw-final-pass

Run a publication-readiness check on a nearly complete piece and deliver a clear ready, almost-ready, or needs-work verdict. Use when the user asks for a final pass, quality gate, or pre-publication check.

Quality

76%

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/cw-final-pass/SKILL.md
SKILL.md
Quality
Evals
Security

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-structured, actionable instruction skill for a publication final pass, with concrete checklists and verdict templates. Its main weaknesses are mild verbosity (including an empty Lessons section) and a broken reference to a context-contract file that is not present.

Suggestions

Remove the empty 'Lessons' placeholder section and deduplicate the 'pass/fail is a recommendation, not a gate' sentiment that appears in both the Purpose and Your Judgment sections.

Fix or remove the reference to '../../references/context-contract.md' — the file is not in the bundle, so either include it as a reference file or inline the relevant requirements so the load step is resolvable.

Add an explicit rule for choosing between 'Ready', 'Almost Ready', and 'Needs More Work' (e.g. thresholds on issue count/severity) so the verdict selection is unambiguous.

DimensionReasoningScore

Conciseness

Mostly efficient with clear checklists, but it includes padding ('This is the last look before it ships'), repeats the 'pass/fail is a recommendation' idea in two places, and carries an empty placeholder 'Lessons' section that adds tokens without value.

3 / 5

Actionability

Provides concrete, actionable guidance — specific evidence/provenance check questions, an exact speed-read protocol, and copy-paste verdict templates — with only minor gaps (no explicit rubric for choosing among the three verdicts).

4 / 5

Workflow Clarity

The check is sequenced into clear stages (load context → content quality → surface polish → speed-read → 20-second pitch → verdict), and as a non-destructive single-purpose check it needs no validation cap; minor gaps are the lack of an explicit ordering rule and the loose 'Collaborative Fixing' loop.

4 / 5

Progressive Disclosure

The body is well-organized with clear section headers, but it points to '../../references/context-contract.md' which does not exist in the bundle, so the single external reference is broken and navigation to the loadable requirements is not actually resolvable.

3 / 5

Total

14

/

20

Passed

Description

78%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 clear, well-structured description that explicitly covers both what the skill does and when to use it with natural trigger terms. It is slightly light on enumerating concrete actions, keeping specificity from the top band.

DimensionReasoningScore

Specificity

Names the domain ('publication-readiness check') and two concrete actions ('Run a publication-readiness check' and 'deliver a clear ready, almost-ready, or needs-work verdict'), but coverage is not comprehensive — it stops at two actions rather than enumerating the checks involved.

3 / 5

Completeness

Explicitly answers both what ('Run a publication-readiness check... deliver a clear ready, almost-ready, or needs-work verdict') and when ('Use when the user asks for a final pass, quality gate, or pre-publication check') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Includes natural phrases a user would say — 'final pass', 'quality gate', 'pre-publication check' — giving good keyword coverage, though a few common synonyms (e.g. 'proofread', 'sign-off') are missing.

4 / 5

Distinctiveness Conflict Risk

The publication-readiness framing and 'final pass'/'pre-publication' triggers carve a mostly distinct niche with minimal conflict risk, though 'quality gate' could overlap with generic review skills.

4 / 5

Total

16

/

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.

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository

EveryInc/compound-writing

Path

skills/cw-final-pass/SKILL.md

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.