craft

Implement phase of RPI methodology. Executes beads-driven task graph using isolated agents for test-first discipline. Use when executing an implementation plan from the draft skill.

Quality

73%

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/craft/SKILL.md

Quality

Content

83%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.

The body is well-structured, actionable, and excels at workflow clarity and progressive disclosure, with explicit gates, remediation feedback loops, and a verified one-level-deep reference. The only modest gaps are minor verbosity in a couple of rationale sections and a few behavioral gate descriptions that could be made more directly runnable.

Dimension	Reasoning	Score
Conciseness	The body is efficient and largely assumes Claude's competence, using tight sections, terse rules, and code/log blocks with little padding; only a few spots (e.g., the 'Context Compaction' rationale and some restated 'When to Use'/'After Implementation' overlaps) could be trimmed, keeping it just below a 5.	4 / 5
Actionability	It provides concrete, executable guidance — a literal orchestration loop, specific beads commands, Task dispatch params, and prompt templates in the reference — with only minor gaps (the inline Remediation steps reference a template in workflow-detail.md rather than reproducing it inline, and some gates are described behaviorally rather than as runnable checks).	4 / 5
Workflow Clarity	The multi-step orchestration loop is clearly sequenced with explicit gate checks (RED/GREEN/VALIDATE), validation feedback loops (remediation → re-validate), escalation checkpoints ('after 2 failed remediations, STOP — ask the user'), and the required execution-log audit trail, fully matching the anchor for clear sequence with feedback loops and checklists.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview that signals a single one-level-deep reference (references/workflow-detail.md) for agent prompt templates and dispatch details, the referenced file exists and contains the promised templates, and navigation is clear with no nested references — matching the clear-overview anchor.	5 / 5
	Total	18 / 20 Passed

Description

63%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.

The description clearly conveys what the skill does and when to use it with a reasonably distinct niche, but its trigger-term coverage is narrow and the action framing leans on methodology language rather than a broad concrete action list. Strengthening the 'Use when' clause with more natural user phrasings would lift the weaker dimensions.

Suggestions

Broaden the 'Use when...' clause with additional natural trigger phrases users would say, such as 'run a beads plan', 'execute the draft plan', or 'build from a plan', to improve trigger-term coverage.

Replace some methodology framing ('RPI methodology', 'test-first discipline') with more concrete action verbs a user would recognize, e.g. 'run isolated agents to write tests then implement them'.

Add a synonym or two for 'implement plan' to reduce dependence on a single trigger scenario and lower conflict risk with sibling skills.

Dimension	Reasoning	Score
Specificity	Names the domain ('Implement phase of RPI methodology', 'beads-driven task graph') and several concrete actions ('Executes beads-driven task graph', 'using isolated agents for test-first discipline'), but the action set is framed around methodology concepts rather than a comprehensive list of distinct operations, leaving minor coverage gaps.	4 / 5
Completeness	It clearly states both what ('Executes beads-driven task graph using isolated agents for test-first discipline') and when ('Use when executing an implementation plan from the draft skill'), with the 'when' explicit but somewhat narrow and tied to a single trigger scenario rather than fully concrete multiple triggers.	4 / 5
Trigger Term Quality	The 'Use when executing an implementation plan from the draft skill' clause supplies a couple of natural trigger phrases ('executing an implementation plan', 'draft skill'), but it lacks common synonyms and file/extension-style variations that a user might naturally say, leaving keyword coverage partial.	3 / 5
Distinctiveness Conflict Risk	The 'beads-driven task graph', 'isolated agents', and 'RPI methodology' framing carves a fairly distinct niche from generic implement/build skills, with only minor overlap risk against other plan-execution or TDD skills.	4 / 5
	Total	15 / 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/craft/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.