utility-skills/rapid-skill-loop
Use when you want to demo the end-to-end Tessl skill workflow quickly. Turn a tiny capability idea into a minimal skill, create exactly one simple eval scenario, run review, optionally optimize once, and then run evals locally or publish. Good triggers include "make a demo skill", "scaffold a skill and eval", and "run the Tessl loop end to end".
90
90%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Quality
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 a strong description that clearly articulates a specific multi-step workflow, provides explicit 'Use when' guidance with natural trigger phrases, and occupies a distinct niche. The description is detailed without being padded, and uses appropriate third-person imperative voice throughout. Minor improvement could be made by slightly tightening the prose, but overall it meets high standards across all dimensions.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: ask which workspace, create a minimal SKILL.md with valid frontmatter, create one eval scenario in Tessl format, run skill review, optionally apply optimization pass, and use publish to trigger evals. | 3 / 3 |
Completeness | Clearly answers both 'what' (the step-by-step workflow of creating a SKILL.md, eval scenario, running review, optimization, and publishing) and 'when' (explicitly stated with 'Use when the goal is to demo the end-to-end Tessl workflow' plus explicit trigger examples). | 3 / 3 |
Trigger Term Quality | Includes natural trigger phrases users would say: 'make a demo skill', 'scaffold a Tessl skill', 'generate one eval scenario', 'show the Tessl flow end to end'. These are realistic user utterances covering multiple variations. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive — targets a very specific niche (Tessl demo workflow) with domain-specific terms like 'Tessl', 'SKILL.md', 'frontmatter', 'skill review', and 'publish to trigger evals'. Unlikely to conflict with other skills. | 3 / 3 |
Total | 12 / 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 strong, highly actionable skill with a clear multi-step workflow, explicit validation gates, and copy-paste-ready templates. Its main weaknesses are moderate redundancy across sections (default constraints, writing rules, and completion checklist overlap significantly) and the monolithic structure that inlines all templates rather than referencing separate files. Overall it would serve well as a practical guide for the Tessl demo workflow.
Suggestions
Consolidate the 'Default Constraints', 'Writing Rules', and 'Completion Checklist' sections to eliminate repeated rules (e.g., 'always ask workspace', 'private: true', 'exactly one scenario' each appear 2-3 times).
Consider extracting the JSON/markdown templates into referenced files (e.g., templates/tile.json.template, templates/criteria.json.template) to reduce inline bulk and improve progressive disclosure.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The skill is reasonably well-structured but contains significant repetition—the JSON format constraints for criteria.json are stated twice (once as templates, once as do/don't lists), the completion checklist largely duplicates the validation step, and the 'Writing Rules' section restates constraints already covered in 'Default Constraints'. Some sections could be consolidated to save tokens. | 2 / 3 |
Actionability | The skill provides fully executable bash commands, complete JSON templates for tile.json and criteria.json, exact markdown templates for SKILL.md and task.md, and specific CLI invocations for each step. Everything is copy-paste ready with clear placeholder conventions. | 3 / 3 |
Workflow Clarity | The 7-step workflow is clearly sequenced with explicit validation checkpoints (step 6 has specific verification commands and a confirmation checklist), error recovery paths (version bump if already exists, fix private flag before publishing), and a clear gate ('Only when valid' pattern before publish). The feedback loop from review back to tightening the skill is explicit. | 3 / 3 |
Progressive Disclosure | The content is well-organized with clear headings and numbered steps, but it's a long monolithic document (~200 lines) with inline templates that could be split into referenced files (e.g., a templates directory for the JSON/markdown shapes). There are no references to external files for advanced usage or template details. | 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.
Reviewed
Table of Contents