init-mode

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

Quality

46%

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

56%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-sequenced, highly concrete two-phase workflow with strong confirmation gating and a useful anti-patterns checklist. Its main weaknesses are unresolved references — the central casting algorithm and four sibling flows point to material that exists neither in the file nor in a bundle — and some redundancy between the Patterns and Examples sections.

Suggestions

Resolve the dangling 'see that section' reference by including the Casting & Persistent Naming algorithm in the body or moving it to a real bundle file (e.g., references/casting.md) with an explicit link — it is the core of Phase 1 yet currently undefined.

Point the 'PRD Mode flow', 'GitHub Issues Mode flow', 'Human Team Members section', and 'Copilot Coding Agent Member section' references at real files or sections, or inline one-line summaries of each.

Trim the union merge-driver rationale ('The `union` merge driver keeps all lines from both sides...') to just the `.gitattributes` block, and compress the Examples section, which re-walks the Patterns steps verbatim.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient — numbered steps, exact paths, and no tutorial-style explanation of known concepts — but it can be tightened: the union merge-driver paragraph explains git behavior Claude already knows ('The `union` merge driver keeps all lines from both sides, which is correct for append-only files...'), and the Example flow (steps 1–9) re-walks the Patterns section nearly verbatim. It is above anchor 2 (no padded sections) but not the lean, fully trimmed fit of 4.	3 / 5
Actionability	Mostly concrete — exact commands (`git config user.name`), an exact `.gitattributes` block, exact registry fields, the exact `## Members` header, and exact ask_user choices — but key details are missing because referenced material does not exist: Phase 1 step 3 defers to 'the Casting & Persistent Naming algorithm (see that section)' and step 8 points to 'PRD Mode flow', 'GitHub Issues Mode flow', 'Human Team Members section', and 'Copilot Coding Agent Member section', none of which appear in the body or the bundle (no references/ files exist). This is 'some concrete guidance but incomplete; missing key details' rather than the minor-gaps fit of 4.	3 / 5
Workflow Clarity	The two-phase sequence is clear with strong checkpoints: a hard 'STOP. Your response ENDS here' gate, an explicit Phase 2 trigger (explicit or implicit confirmation), a re-propose loop for 'add someone'/'change a role', and a destructive-op guard (no files before confirmation), plus an Anti-Patterns checklist. It falls short of 5 only because there is no post-creation validation step (e.g., verifying the `## Members` header and casting files were written correctly).	4 / 5
Progressive Disclosure	The single file is well-sectioned (Context, Patterns, Examples, Anti-Patterns) but there are no bundle files (references/, scripts/, assets/ are absent) and every cross-reference in the body — 'see that section' for the casting algorithm, the four sibling-mode flows, and `.squad/templates/` (a runtime path, not a bundle file) — is dangling. Structure exists, but navigation to the referenced material is broken, matching anchor 3 ('some structure... references present but not clearly signaled').	3 / 5
	Total	13 / 20 Passed

Description

37%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 correctly identifies the domain and two-phase shape of the skill but communicates almost nothing actionable: no concrete capabilities, no natural trigger terms, and no 'when to use' guidance. It functions as an internal label rather than a discovery mechanism.

Suggestions

State concrete actions: e.g., 'Proposes a team roster with cast names, confirms it with the user via the ask_user tool, then creates the .squad/ directory structure, casting state, and agent histories.'

Add an explicit 'Use when...' clause mirroring the body's activation condition, e.g., 'Use when .squad/team.md does not exist or has no members under ## Members.'

Include natural trigger terms users would say — 'team setup', 'initialize the squad', 'cast a team', '.squad/team.md' — instead of internal phase labels.

Dimension	Reasoning	Score
Specificity	The description names the domain ('Team initialization flow') and two phase labels ('Phase 1 proposal + Phase 2 creation'), but these are generic structural markers rather than concrete actions — nothing about proposing a roster, confirming with the user, or creating the `.squad/` structure. It matches the anchor 'Names the domain but actions are minimal or generic' and falls short of 3, which requires 1-2 genuinely concrete actions.	2 / 5
Completeness	A rough 'what' is present (team initialization via a two-phase flow) but the 'when' is entirely absent — there is no 'Use when...' clause and no hint of the activation condition (no `.squad/team.md` or empty roster). Per the rubric guideline, a missing explicit trigger caps completeness at 3; it does not reach 4 because 'when' is not even weakly worded, only inferable from the name.	3 / 5
Trigger Term Quality	Keywords are internal jargon ('initialization', 'Phase 1 proposal', 'Phase 2 creation') with no natural phrases a user would actually say, such as 'set up a team', 'cast a team', or '.squad'. It has roughly two generic keywords while missing the natural user vocabulary, matching anchor 2; it is above 1 because 'team' and 'initialization' are at least domain-relevant.	2 / 5
Distinctiveness Conflict Risk	'Team initialization flow' carves out a niche within the squad system, but the wording is generic enough to overlap with other team-setup or onboarding skills. It fits anchor 3 ('somewhat specific but could still overlap with similar skills') — more distinctive than anchor 2's broad 'helps with document files' but lacking the clear, distinct triggers of anchor 4.	3 / 5
	Total	10 / 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: bradygaster/squad
Path: .copilot/skills/init-mode/SKILL.md
Commit: 29e69f5

Reviewed: 5 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.