write
Write blog posts from session insights with multi-perspective analysis.
62
45%
Does it follow best practices?
Impact
88%
1.07xAverage score across 3 eval scenarios
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./write/skills/write/SKILL.mdQuality
Discovery
32%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 too terse and vague to effectively guide skill selection. It lacks a 'Use when...' clause, doesn't define what 'session insights' means, and doesn't list concrete actions beyond writing blog posts. The term 'multi-perspective analysis' is unclear jargon that wouldn't help Claude or users identify when to use this skill.
Suggestions
Add an explicit 'Use when...' clause with natural trigger terms, e.g., 'Use when the user wants to turn meeting notes, workshop sessions, or event takeaways into blog content.'
Clarify what 'session insights' refers to (e.g., therapy sessions, conference talks, workshop notes) to reduce ambiguity and improve distinctiveness.
List specific concrete actions beyond just 'write blog posts', such as 'Summarizes key themes, synthesizes multiple viewpoints, and drafts structured blog posts with headings and takeaways.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Names the domain ('blog posts from session insights') and one action ('write blog posts') with a modifier ('multi-perspective analysis'), but doesn't list multiple concrete actions or elaborate on what 'session insights' or 'multi-perspective analysis' entail. | 2 / 3 |
Completeness | It partially addresses 'what' (write blog posts from session insights) but there is no 'Use when...' clause or any explicit trigger guidance for when Claude should select this skill, which per the rubric caps completeness at 2, and the 'what' itself is weak enough to warrant a 1. | 1 / 3 |
Trigger Term Quality | 'Blog posts' is a natural keyword users might say, but 'session insights' and 'multi-perspective analysis' are vague and not terms users would naturally use. Missing common variations like 'write a blog', 'content from notes', 'meeting notes to blog', etc. | 2 / 3 |
Distinctiveness Conflict Risk | 'Session insights' and 'multi-perspective analysis' add some specificity that distinguishes it from a generic blog writing skill, but 'session insights' is ambiguous (therapy sessions? meeting sessions? conference sessions?) which could cause overlap or misfires. | 2 / 3 |
Total | 7 / 12 Passed |
Implementation
57%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill provides a well-organized multi-phase workflow for transforming session insights into blog posts, with good progressive disclosure and clear phase sequencing. However, it leans heavily on abstract notation (mathematical formulas for the Prothesis protocol) and lacks concrete, executable examples of what the actual content transformation looks like in practice. The actionability would benefit significantly from a worked example showing input session content mapped to output blog structure.
Suggestions
Replace or supplement the mathematical Prothesis notation (G(U) → C, etc.) with a concrete worked example showing an actual session insight being analyzed from multiple perspectives and transformed into blog content.
Add a concrete example of a draft output in the Draft Generation phase, showing what the Hook → Context → Framework → Application → Implications structure looks like with sample text.
Remove the 'What Gets Filtered' table—Claude already knows not to include debugging steps and tool invocations in blog posts; this wastes tokens on obvious guidance.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably structured but includes some unnecessary elements like the mathematical notation for the Prothesis protocol phases, the 'When to Use / Skip when' section that over-explains, and the 'What Gets Filtered' table which states obvious things Claude already knows (e.g., don't include debugging steps in blog posts). | 2 / 3 |
Actionability | The workflow provides a clear sequence of phases and references specific tools (/frame, /gap, Edit, Write), but the actual execution guidance is abstract rather than concrete. There are no executable examples of content transformation, no sample draft structure with actual text, and the Prothesis protocol is described in mathematical notation rather than actionable steps. | 2 / 3 |
Workflow Clarity | The phases are clearly sequenced with a summary table and numbered steps, and there are exit conditions for the refinement loop. However, validation is deferred to Phase 7 with no intermediate checkpoints, and the feedback loop in Phase 6 lacks specifics on how to handle structural vs incremental changes beyond a brief mention of option versions. | 2 / 3 |
Progressive Disclosure | The skill provides a clear overview with well-signaled references to external files (prothesis/skills/frame/SKILL.md, references/workflow.md) and keeps the main content at an appropriate summary level. Navigation between phases and integration points is clearly structured. | 3 / 3 |
Total | 9 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- jongwony/epistemic-protocols
- Commit
9342160
- 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.