create-rfc
Creates structured Request for Comments (RFC) documents for proposing and deciding on significant changes. Use when the user says "write an RFC", "create a proposal", "I need to propose a change", "draft an RFC", "document a decision", or needs stakeholder alignment before making a major technical or process decision. Do NOT use for TDDs/implementation docs (use technical-design-doc-creator instead), README files, or general documentation.
79
73%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./packages/skills-catalog/skills/(creation)/create-rfc/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is an excellent skill description that hits all the marks. It provides specific actions, rich natural trigger terms, explicit 'Use when' and 'Do NOT use' clauses, and clear differentiation from related skills. It serves as a strong example of how to write a skill description that enables accurate skill selection from a large pool.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description specifies a concrete action ('Creates structured Request for Comments (RFC) documents') and clarifies the purpose ('proposing and deciding on significant changes'). It also explicitly distinguishes what it does NOT do, adding further specificity. | 3 / 3 |
Completeness | Clearly answers both 'what' (creates structured RFC documents for proposing significant changes) and 'when' (explicit 'Use when' clause with multiple trigger phrases). Also includes a 'Do NOT use' clause that further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural trigger terms: 'write an RFC', 'create a proposal', 'propose a change', 'draft an RFC', 'document a decision', 'stakeholder alignment', 'major technical or process decision'. These are phrases users would naturally say. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit boundary-setting: it names a specific document type (RFC), differentiates from TDDs/implementation docs by referencing a sibling skill ('technical-design-doc-creator'), and excludes READMEs and general documentation. Very unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
47%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
The skill has a well-structured workflow with clear sequencing and validation checkpoints, which is its strongest aspect. However, it is significantly over-verbose, explaining concepts Claude already understands (RFC purpose, RFC vs TDD, what good background looks like), repeating key points multiple times, and including low-value content like example trigger prompts in three languages. The core actionable content—the actual section templates—is deferred to an external file, making this file more of a lengthy preamble than a self-contained guide.
Suggestions
Cut the content by 40-50%: remove the RFC vs TDD comparison table, the 'When to Use' and 'Do NOT use' sections (already in frontmatter description), the example prompts section, and deduplicate repeated guidance (e.g., 'do nothing' option, language adaptation).
Inline at least a condensed version of the section templates from references/section-templates.md so the skill is actionable without requiring the external file.
Consolidate the anti-patterns into a brief bullet list rather than full BAD/GOOD example blocks—Claude can infer good RFC writing from the template and checklist alone.
Remove the 'Language Adaptation' section and example prompts in multiple languages—a single bullet point noting 'Match the user's language' is sufficient.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is extremely verbose at ~250+ lines. It explains concepts Claude already knows (what an RFC is, RFC vs TDD distinctions at length), includes extensive anti-pattern examples that are general knowledge, lists example prompts in three languages that add no instructional value, and repeats guidance across multiple sections (e.g., 'do nothing' option mentioned 3 times, language adaptation mentioned multiple times). | 1 / 3 |
Actionability | The skill provides a structured workflow and a quality checklist, which are concrete. However, the actual section templates are deferred to an external file (references/section-templates.md) rather than being inline, and the AskQuestion JSON block is a schema example rather than truly executable guidance. The document structure is clear but the core deliverable content (the actual RFC template) is missing from this file. | 2 / 3 |
Workflow Clarity | The 5-step interactive workflow is clearly sequenced (gather context → validate mandatory fields → detect type → generate → offer next steps), with explicit validation in Step 2 for mandatory fields and a comprehensive quality checklist before finalizing. The feedback loop of asking for missing information before generating is well-defined. | 3 / 3 |
Progressive Disclosure | There is one external reference (references/section-templates.md) which is appropriate, but the main file itself contains too much inline content that could be split out (anti-patterns, RFC type tables, example prompts). The structure has clear headers but the sheer volume of inline content undermines the progressive disclosure principle. | 2 / 3 |
Total | 8 / 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
- tech-leads-club/agent-skills
- Commit
906a57d
- 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.