moai-kanban-foreman

One unattended kanban foreman iteration: watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report. This is the body the project's loop.md driver invokes each iteration of a bare /loop; it can also be invoked directly to test one cycle by hand.

Quality

78%

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 ./.claude/skills/moai-kanban-foreman/SKILL.md

Quality

Content

81%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 a well-structured, actionable runbook with explicit validation feedback loops and one clearly signaled external reference. It is efficient and assumes Claude's intelligence, with only minor trim opportunities in rationale prose and the worker-prompt specification.

Dimension	Reasoning	Score
Conciseness	The body is dense with operational specifics and assumes Claude's competence (no basic-concept explanations), but rationale prose such as "that is the mechanical guarantee that the loop cannot stop and ask" and the checksum-pool justification could be trimmed slightly.	4 / 5
Actionability	Concrete executable elements abound — the Monitor shell command, `moai todo list --json`, `moai todo done <t-id>`, and the dispatch address block — but the worker standing orders are conveyed as prose rather than a copy-paste prompt template, leaving minor gaps.	4 / 5
Workflow Clarity	The seven-step iteration is explicitly sequenced with validation checkpoints (step 3 collect-before-dispatch, step 6 collect-on-evidence with a gap→keep-picked feedback loop) plus a hard-boundaries checklist and a failure-handling feedback loop, matching the top anchor.	5 / 5
Progressive Disclosure	Clean sectioned structure with one clearly signaled one-level-deep external reference (the kanban-dispatch rule file) for the dispatch protocol; the body is a single overview file with no nested references, though the reserved Factory seam and Running-unattended prose could be slightly tighter.	4 / 5
	Total	17 / 20 Passed

Description

75%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 is specific, distinct, and action-rich, but its trigger guidance lives in a separate when_to_use field rather than an inline "Use when..." clause, which caps completeness. Specificity and distinctiveness are strong; voice is correctly third person.

Suggestions

Fold an explicit "Use when..." trigger clause into the description itself (e.g. "Use when a bare /loop kanban foreman iteration fires or the operator asks for a single manual foreman pass"), or treat the when_to_use field as the canonical trigger surface and note that relationship, to lift completeness above 3.

Add one or two more natural user-facing synonyms (e.g. "foreman pass", "backlog") to broaden trigger-term coverage toward a 5.

Dimension	Reasoning	Score
Specificity	"watch the backlog queue, dispatch the next operator-picked card to an isolated worker, collect completion evidence on read (not on claims), and report" lists multiple concrete actions with comprehensive coverage of the iteration's behavior.	5 / 5
Completeness	The description gives a clear "what" (watch/dispatch/collect/report) but the "when" is only weakly implied via "the loop.md driver invokes each iteration of a bare /loop"; no explicit "Use when..." trigger clause lives in the description field itself, capping completeness at 3 per the rubric guideline.	3 / 5
Trigger Term Quality	Natural terms like "kanban foreman", "backlog queue", and "bare /loop" appear and match what an operator would say, though a few common variations (e.g. "foreman pass", "backlog") are not all present.	4 / 5
Distinctiveness Conflict Risk	"One unattended kanban foreman iteration" with dispatch/evidence-on-read semantics is a clear niche with distinct triggers and minimal overlap risk with other skills.	5 / 5
	Total	17 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: modu-ai/moai-adk
Path: .claude/skills/moai-kanban-foreman/SKILL.md
Commit: 2213871

Reviewed: 1 day 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.