init-mode

Team initialization flow (Phase 1 proposal + Phase 2 creation)

Quality

63%

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 ./.copilot/skills/init-mode/SKILL.md

Quality

Content

77%

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 two-phase workflow with strong validation gates and feedback loops. Its main weakness is progressive disclosure: it leans on a referenced casting section that does not exist in the document and carries inline detail that a reference file could absorb.

Suggestions

Add the missing 'Casting & Persistent Naming algorithm' section that step 3 references, or move it into a dedicated reference file and link to it explicitly so the '(see that section)' pointer resolves.

Extract the detailed post-setup input-sources block and the .gitattributes merge-driver recipe into a reference file (e.g. references/team-setup.md) and link from SKILL.md to reduce inline bulk.

Tighten the casting sub-steps into a concise checklist so the propose-team flow stays scannable.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence (no explaining of basic concepts), but the casting sub-steps, the post-setup input-sources enumeration, and the merge-driver explanation add detail that could be tightened or offloaded to references.	2 / 3
Actionability	Concrete, executable guidance throughout: `git config user.name`, exact `.gitattributes` merge=union blocks, the `## Members` header requirement, `ask_user` choices/question text, and `registry.json` entry fields are all copy-paste ready.	3 / 3
Workflow Clarity	Phase 1 and Phase 2 are explicitly sequenced with a hard validation checkpoint (the '⚠️ STOP... wait for confirmation' gate) and a feedback loop ('If the user said add someone... go back to Phase 1 step 3'), reinforced by the Anti-Patterns section.	3 / 3
Progressive Disclosure	Sections are well-organized (Context, Patterns, Examples, Anti-Patterns) but the document is monolithic with no bundle files, and it references 'the Casting & Persistent Naming algorithm (see that section)' which is not actually present in SKILL.md — a dangling, one-level reference that resolves to nothing.	2 / 3
	Total	10 / 12 Passed

Description

50%

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 correctly identifies the skill's domain and two-phase shape but is written in internal process jargon rather than user-facing trigger language, and it omits any 'Use when' guidance. It is distinguishable but under-specified for triggering.

Suggestions

Add a 'Use when...' clause with natural trigger phrasing, e.g. 'Use when no .squad/team.md exists or the team has no members, to set up or re-propose the squad.'

Replace internal jargon ('Phase 1 proposal + Phase 2 creation') with concrete user-facing actions like 'propose a team roster, confirm it, and create the .squad/ structure'.

Include natural trigger terms users would actually say ('set up the team', 'create a squad', 'initialize the team') to improve trigger matching and distinctiveness.

Dimension	Reasoning	Score
Specificity	It names the domain (team initialization) and two actions (Phase 1 proposal, Phase 2 creation), but does not enumerate the concrete operations (propose roster, confirm via ask_user, create .squad/ structure, seed agents).	2 / 3
Completeness	It states what the skill does (team initialization flow) but provides no 'Use when...' clause or explicit trigger guidance for when Claude should invoke it, capping completeness at 2 per the rubric guideline.	2 / 3
Trigger Term Quality	'Team initialization' is a somewhat natural phrase, but the prominent terms 'Phase 1 proposal' and 'Phase 2 creation' are internal jargon users would not say, and common variations like 'set up the team', 'create a squad', or 'initialize the team' are absent.	2 / 3
Distinctiveness Conflict Risk	The 'team initialization' niche is fairly specific, but without explicit triggers it could overlap with sibling orchestration/team skills (other squad modes) that share the same domain vocabulary.	2 / 3
	Total	8 / 12 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: bradygaster/squad
Path: .copilot/skills/init-mode/SKILL.md
Commit: e23dd92

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.