fabric-document
Synthesizes all pipeline handoffs into a single human-readable project brief. Use when user says "generate docs", "create documentation", "document the project", or after validation passes. Do NOT use for deployment (use fabric-deploy) or architecture design (use fabric-design).
68
83%
Does it follow best practices?
Impact
—
No eval scenarios have been run
Passed
No known issues
Quality
Discovery
89%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 a well-crafted description that excels in completeness and distinctiveness, with explicit trigger phrases and clear negative boundaries to prevent skill conflicts. The main weakness is that the 'what' portion could be more specific about the concrete actions performed (e.g., what sections the brief contains, what pipeline handoffs are aggregated). Overall it is a strong description that would perform well in skill selection.
Suggestions
Add more specific concrete actions to the 'what' portion, e.g., 'Synthesizes pipeline handoffs into a project brief including architecture decisions, validation results, and deployment readiness summaries.'
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | It names the domain ('pipeline handoffs', 'project brief') and describes one action ('synthesizes into a human-readable project brief'), but does not list multiple specific concrete actions like what the brief contains or what formats it supports. | 2 / 3 |
Completeness | Clearly answers both 'what' (synthesizes pipeline handoffs into a human-readable project brief) and 'when' (explicit trigger phrases and conditions). Also includes helpful negative boundaries with 'Do NOT use for' clauses. | 3 / 3 |
Trigger Term Quality | Includes natural trigger terms users would say: 'generate docs', 'create documentation', 'document the project', and the contextual trigger 'after validation passes'. These are realistic phrases a user would use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with explicit negative boundaries referencing other skills (fabric-deploy, fabric-design), a clear niche around pipeline documentation synthesis, and specific trigger terms that reduce overlap risk. | 3 / 3 |
Total | 11 / 12 Passed |
Implementation
77%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This is a well-structured documentation skill that clearly defines a single deliverable, provides a clean three-step workflow, and includes good constraints to prevent scope creep. Its main weaknesses are the lack of a concrete example showing what polished output looks like (before/after an AGENT:FILL marker replacement) and the missing referenced template file. The verification checklist is a strong inclusion that serves as an effective validation step.
Suggestions
Add a brief before/after example showing how an `<!-- AGENT: FILL -->` marker should be replaced with narrative polish, so the expected output quality is concrete.
Include the referenced `references/documentation-templates.md` in the bundle or inline the key template structure so the skill is self-contained.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is lean and efficient. It assumes Claude knows how to read files, edit markdown, and synthesize information. No unnecessary explanations of what documentation is or how markdown works. Every section serves a clear purpose. | 3 / 3 |
Actionability | The skill provides clear steps and specific file paths, but lacks executable code or concrete examples of what polished output should look like. The reference to 'references/documentation-templates.md' for the template is good but the template isn't included, and no example of a completed section or the AGENT:FILL marker replacement is shown. | 2 / 3 |
Workflow Clarity | The three-step workflow is clearly sequenced: read inputs → polish pre-generated brief → verify completeness. The verification step acts as a validation checkpoint with 5 explicit questions. The constraint that the brief is pre-generated with AGENT:FILL markers makes the workflow unambiguous. | 3 / 3 |
Progressive Disclosure | The skill references 'references/documentation-templates.md' for the template but this file is not provided in the bundle, making it impossible to verify. The skill itself is well-structured with clear sections, but the missing bundle file is a gap. The reference to the template is one-level deep and clearly signaled, which is good. | 2 / 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.
Validation — 11 / 11 Passed
Validation for skill structure
No warnings or errors.
- Repository
- microsoft/fabric-task-flows
- Commit
b986f41
- 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.