team-assembly

Select the minimum complete reviewer team for a Fallow change based on touched paths, contracts, integrations, and risk.

Quality

68%

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/team-assembly/SKILL.md

Quality

Content

78%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 exceptionally concise and well-structured with a clear sequenced workflow and appropriately signaled external reference, but the mapping decision logic is underspecified in the body itself, slightly limiting actionability.

Suggestions

Add a brief inline heuristic or one-line summary of how touched paths map to reviewer domains so the skill is actionable without fully loading the external routing doc.

Insert an explicit validation step (e.g., 'Confirm the team covers every touched path and every changed contract before briefing') to strengthen workflow clarity.

Clarify what 'synthesize verdicts without replacing blocks with majority votes' means concretely — give a one-line rule for how conflicting verdicts are resolved.

Dimension	Reasoning	Score
Conciseness	The body is lean (~13 lines), assumes Claude's competence, and contains no padding or over-explanation of concepts Claude already knows — every token earns its place.	5 / 5
Actionability	It names concrete artifacts ('docs/development/review-routing.md', 'the diff', 'controlling plan', 'primary source files') and gives a followable procedure, but the core decision logic ('Map touched paths and behavioral effects to reviewer domains') is not executable without the external routing doc, leaving key details missing.	3 / 5
Workflow Clarity	A clear six-step numbered sequence with a closing guard clause ('Do not select reviewers only from filenames...'), but it lacks an explicit validation checkpoint confirming the assembled team is complete/correct before briefing reviewers.	4 / 5
Progressive Disclosure	Under 50 lines, single-purpose, with a well-organized heading, numbered list, and guard clause; the one external reference (review-routing.md) is one level deep and clearly signaled inline, and no bundle files are needed.	5 / 5
	Total	17 / 20 Passed

Description

58%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 concise, third-person, and specific about the selection criteria, but it omits an explicit 'when to use' trigger clause, which limits its completeness and trigger-term coverage.

Suggestions

Add an explicit 'Use when...' clause stating when Claude should invoke this skill (e.g., 'Use when assembling reviewers for a Fallow change or when the user asks who should review a diff').

Include natural trigger synonyms such as 'code review', 'assign reviewers', or 'who reviews this change' to improve keyword coverage.

Surface additional concrete actions beyond 'Select' — e.g., 'brief reviewers', 'parallelize independent reviews', 'synthesize verdicts' — to broaden specificity.

Dimension	Reasoning	Score
Specificity	Names the domain (reviewer team selection) and several concrete selection criteria — 'touched paths, contracts, integrations, and risk' — but frames them as inputs to a single 'Select' action rather than listing multiple distinct actions, leaving minor coverage gaps.	4 / 5
Completeness	Clearly answers 'what' (select the minimum complete reviewer team) but provides no explicit 'Use when...' trigger clause; per the rubric, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant domain terms like 'reviewer team', 'Fallow change', 'contracts', and 'integrations', but misses common natural-user variations such as 'code review', 'assign reviewers', or 'who should review this'.	3 / 5
Distinctiveness Conflict Risk	The 'Fallow change' framing and reviewer-team selection niche make it mostly distinct from generic skills, with only minor overlap risk against broad code-review skills.	4 / 5
	Total	14 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: fallow-rs/fallow
Path: .claude/skills/team-assembly/SKILL.md
Commit: 7e1e075

Reviewed: 3 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.