CtrlK
BlogDocsLog inGet started
Tessl Logo

paper-orchestration

Use when a research-writing task spans multiple sections, medium-sized revisions, full-paper drafting, or repeated quality failures

66

Quality

78%

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/paper-orchestration/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

The body is a strong, actionable orchestration controller with concrete templates, explicit gates, and clear stage sequencing. Its only weakness is mild redundancy across the multi-agent, task-packet, and common-failure sections.

Suggestions

State the disjoint-write-ownership rule once (in the Multi-Agent Chapter Gate) and reference it from the Task Packet section instead of repeating it.

Trim Common Failures entries that merely restate earlier gates (e.g. the sequential-writing failure duplicates the Multi-Agent Chapter Gate) to keep the list focused on genuinely distinct pitfalls.

DimensionReasoningScore

Conciseness

The body is operational and free of concept-explaining fluff, but disjoint-write-ownership is restated in both the Multi-Agent Chapter Gate and the Task Packet section, and several Common Failures restate earlier gating rules, so it could be tightened.

2 / 3

Actionability

Concrete artifact paths (plan/progress.md, plan/chapter-architecture.md, plan/task-packets/), a copy-paste task-packet template, a chapter-file format with min_chars/agent/placeholders fields, and an audit template give fully executable, specific guidance.

3 / 3

Workflow Clarity

The S0–S5 Stage Detection table sequences work with triggers and required next skills, the Review Gates define two explicit checks with a fix-before-proceeding feedback loop, and the degraded-mode fallback ("stop and ask the user") provides clear error recovery.

3 / 3

Progressive Disclosure

No bundle files exist and none are needed; the skill is a single cohesive controller with well-organized sections and no nested references, so the inline structure is appropriate for an orchestration skill.

3 / 3

Total

11

/

12

Passed

Description

72%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.

The description has a strong explicit trigger clause and a distinct niche, but it tells Claude when to activate without saying what the skill actually does. Adding a concise capability statement would lift completeness and specificity.

Suggestions

Prefix the trigger clause with a short capability statement, e.g. "Controls the research-writing workflow via stage detection, task packets, and review gates. Use when..."

Name one or two concrete actions (e.g. "dispatches per-chapter agents", "enforces review gates") so the "what" is explicit, not just the "when".

DimensionReasoningScore

Specificity

The description names the domain and a few action-like phrases ("medium-sized revisions", "full-paper drafting") but never enumerates concrete capabilities such as gating, task packets, or multi-agent dispatch, so it stops at naming domain and some actions rather than a comprehensive list.

2 / 3

Completeness

It has an explicit "Use when..." trigger clause (the "when") but omits any statement of what the skill does, so the "what" is only implied rather than answered.

2 / 3

Trigger Term Quality

Phrases like "research-writing task", "multiple sections", "medium-sized revisions", and "full-paper drafting" are natural terms a user would say when requesting multi-section paper work, giving good coverage of common variations.

3 / 3

Distinctiveness Conflict Risk

The orchestration niche (multi-section, full-paper drafting, repeated quality failures) is distinct from the individual writing skills it coordinates, making wrong-skill triggering unlikely.

3 / 3

Total

10

/

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.