draft

Plan phase of RPI methodology. Consumes research artifact or topic and produces compact implementation plan with test specs and Agent Context blocks. Use after research or to start planning a non-trivial feature.

Quality

79%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./tiles/crafter/skills/draft/SKILL.md

Quality

Content

75%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable workflow skill with clear sequencing and good reference discipline. Its main weakness is conciseness — conceptual rationale and content duplicated from template.md inflate the body.

Suggestions

Remove the 'Context Compact' section and state the 'audit trail vs execution source of truth' distinction once near Step 3 instead of repeating it across Steps 3, 3b, 4, and After Planning.

Defer the inlined test-spec good/bad examples (L3/L4) and the Agent Context required-fields list to template.md, where they already exist, to eliminate duplication.

Trim the 'Phase Boundaries' and 'Anti-Patterns to Avoid' sections, which restate guidance already covered in template.md, or compress them into a brief pointer.

Dimension	Reasoning	Score
Conciseness	Mostly efficient but includes unnecessary explanation and repetition — the 'Context Compaction' rationale, repeated 'audit trail vs execution source of truth' statements, and restated phase-boundary/anti-pattern guidance that already lives in template.md could be tightened.	3 / 5
Actionability	Highly actionable: concrete beads commands (beads:epic, beads:dep, beads:label, beads:ready), exact issue decomposition rules (TDD phases get 3 issues: Write Tests → Implement → Validate), explicit labels, and a fully worked 6-phase example tree; a beads-unavailable fallback is also specified.	5 / 5
Workflow Clarity	Clear numbered sequence (Steps 1–5 plus 3b) with checkpoints — a beads availability check with fallback, a review/approval gate, and per-phase verification checklists; not a 5 because true validate→fix→retry feedback loops are delegated to /craft rather than present in /draft's own workflow.	4 / 5
Progressive Disclosure	Good structure with one-level-deep, well-signaled references to references/template.md for the full template and issue description templates; a minor organization gap is the duplication of test-spec good/bad examples, Agent Context field lists, and phase-boundary guidance that also appear in template.md.	4 / 5
	Total	16 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, concrete description that clearly states what the skill does and when to use it, with natural trigger phrases. Minor gaps in action coverage and synonym breadth keep it just below the top anchor on two dimensions.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — 'Consumes research artifact or topic', 'produces compact implementation plan with test specs and Agent Context blocks' — naming the RPI plan domain with specific outputs; falls short of 5 because it omits other core actions like creating the beads task graph.	4 / 5
Completeness	Explicitly answers both what ('Plan phase of RPI methodology... produces compact implementation plan with test specs and Agent Context blocks') and when ('Use after research or to start planning a non-trivial feature') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Natural phrases a user would say are present ('plan', 'draft plan', 'implementation plan', 'after research') with good coverage; not a 5 because synonyms like 'spec', 'roadmap', or 'design' are missing.	4 / 5
Distinctiveness Conflict Risk	Scoped to the RPI methodology planning niche with distinct triggers, so mostly distinct; not a 5 because the bare word 'plan' is generic and could overlap with other planning skills.	4 / 5
	Total	17 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: ericjohnolson/tessl-test
Path: tiles/crafter/skills/draft/SKILL.md
Commit: 2a98cc1

Reviewed: 4 days ago

Table of Contents

Discovery Implementation Validation

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.