CtrlK
BlogDocsLog inGet started
Tessl Logo

coordinator-init-mode

The complete two-phase Init Mode protocol the Squad coordinator runs when no team exists yet in the current repo. Phase 1 = propose the team (no files created, wait for user confirm). Phase 2 = create .squad/ scaffolding, casting state, .gitattributes for merge drivers, and the always-on built-ins (Scribe, Ralph, Rai, Fact Checker). Loaded on demand when the coordinator detects no .squad/team.md exists.

64

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.squad/skills/coordinator-init-mode/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

82%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 highly actionable with concrete commands and copy-paste-ready blocks, a well-sequenced two-phase workflow with strong confirmation gating, and clean section structure. The main gaps are minor: some redundancy and the absence of an explicit post-setup verification checkpoint.

Suggestions

Add an explicit post-setup verification step in Phase 2 (e.g., confirm .squad/ structure and the exact '## Members' header exist) to close the validation gap and push workflow_clarity toward 5.

Trim redundancy such as the repeated eager-execution exception and condense the roster example block to improve conciseness.

Consider extracting the casting algorithm detail to a bundled reference file so progressive_disclosure can score higher with a clearly signaled one-level reference.

DimensionReasoningScore

Conciseness

Assumes Claude's competence (no explanation of git, .gitattributes, or squad basics) and keeps detail action-relevant, but carries minor redundancy such as re-stating the eager-execution exception and a full roster example block, fitting anchor 4 rather than the lean anchor 5.

4 / 5

Actionability

Provides fully executable, copy-paste-ready guidance including the exact .gitattributes block, the ask_user question shape, directory structure, and registry.json entry fields, matching anchor 5.

5 / 5

Workflow Clarity

Clear two-phase sequence with explicit checkpoints (Phase 1 STOP gate, Phase 2 confirmation trigger, re-propose loop) and the hard-coded team.md header requirement, but it lacks a post-creation verification step, leaving a minor validation gap per anchor 4.

4 / 5

Progressive Disclosure

Well-organized into clear Phase 1 / Phase 2 sections with one-level references to templates and squad.agent.md, and no nested skill-bundle references; with no bundle files present the structure is appropriately self-contained, fitting anchor 4.

4 / 5

Total

17

/

20

Passed

Description

71%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 answers both what and when with an explicit load condition, though its trigger framing is system-detected rather than built from natural user phrases. It is third-person and free of fluff, with only modest gaps in keyword/trigger coverage.

Suggestions

Add a user-facing 'Use when...' clause with natural phrases (e.g., 'Use when the user wants to squadify a fresh repo or set up a new team') to improve trigger_term_quality and completeness.

Surface common synonyms users might say (e.g., 'squad setup', 'initialize a squad', 'new team') alongside the existing technical terms.

Tighten the phase list into a more comprehensive enumeration of concrete actions to push specificity toward anchor 5.

DimensionReasoningScore

Specificity

Lists several concrete actions across the two phases ('propose the team', 'create .squad/ scaffolding, casting state, .gitattributes for merge drivers', names the four built-ins) with only minor coverage gaps, fitting anchor 4 rather than the fully comprehensive anchor 5.

4 / 5

Completeness

Clearly answers 'what' (two-phase protocol with phase contents) and provides an explicit 'when' ('Loaded on demand when the coordinator detects no .squad/team.md exists'), but the when is a load-condition rather than a user-facing 'Use when...' trigger phrase, fitting anchor 4.

4 / 5

Trigger Term Quality

Contains relevant terms ('Init Mode', 'no team exists yet', '.squad/team.md', 'fresh repo') but the trigger is system-detected rather than user-spoken, and it misses natural variations or synonyms users would say, matching anchor 3.

3 / 5

Distinctiveness Conflict Risk

Occupies a clear niche (Squad coordinator Init Mode) with a distinct, specific trigger (no .squad/team.md exists), giving it minimal conflict risk with other skills per anchor 5.

5 / 5

Total

16

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
bradygaster/squad
Reviewed

Table of Contents

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.