CtrlK
BlogDocsLog inGet started
Tessl Logo

distributed-mesh

How to coordinate with squads on different machines using git as transport

48

Quality

52%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./.copilot/skills/distributed-mesh/SKILL.md
SKILL.md
Quality
Evals
Security

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.

A well-structured, conceptually coherent skill with an excellent deterministic workflow, undermined by two issues: heavy repetition of the same scope-fencing warnings (token waste), and references to bundled files that are not present in the skill directory, which makes the core setup steps unexecutable as written. The unique distributed-coordination knowledge itself is valuable and appropriately non-obvious.

Suggestions

Ship the referenced bundle files (mesh.json.example, sync-mesh.sh, sync-mesh.ps1) in scripts/ or references/, or remove the copy/init steps — the workflow currently depends on resources that don't exist.

Consolidate the repeated 'copy, don't generate' and 'no code/tests/modules' warnings into one authoritative SCOPE section and cut the duplicates from Patterns, Steps 3/6, and Anti-Patterns.

Move the conceptual Patterns/Examples/Anti-Patterns material into a one-level-deep reference file (e.g. references/patterns.md) so SKILL.md stays a lean overview plus the deterministic workflow, and add a post-copy validation checkpoint (e.g. verify mesh.json parses and scripts are executable).

DimensionReasoningScore

Conciseness

The conceptual material (zones, trust boundaries, write partitioning) is domain-specific knowledge Claude would not already have, so it earns its place. But scope-fencing is repeated to the point of padding: 'copy the scripts, do NOT generate them' appears ~7 times (SCOPE, Patterns, Steps 3 and 6, Anti-Patterns), and the 'no code, no tests, no modules' list is restated three times. Mostly efficient but could be tightened considerably.

3 / 5

Actionability

The workflow itself is highly concrete — verbatim questions to ask, a full mesh.json schema with example, per-platform init commands, and a copy-paste decision-entry template. However, key execution details are missing in practice: the referenced bundled files (mesh.json.example, sync-mesh.sh, sync-mesh.ps1) do not exist in this skill's bundle (references/, scripts/, assets/ are absent), so Steps 2–4 cannot actually be executed as written.

3 / 5

Workflow Clarity

The AGENT WORKFLOW is a clean, ordered 6-step sequence with explicit skip conditions ('Skip this step if no Zone 2 squads...'), platform variants, and a hard STOP step — better sequenced than most. It falls short of a 5 only on validation: no checkpoint verifying mesh.json is valid, that the script copies succeeded, or that the --init scaffold landed, only the final completion message.

4 / 5

Progressive Disclosure

Sections are well-labeled and navigation within the file is easy, and the domain concepts genuinely need explaining. But the ~280-line file is monolithic: the Patterns/Examples/Anti-Patterns conceptual material (roughly half the body) is the kind of content that belongs in one-level-deep reference files, and the files the body does reference (mesh.json.example, sync scripts) are absent from the bundle, so the only 'references' present are broken paths.

3 / 5

Total

13

/

20

Passed

Description

48%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 identifies a distinctive niche (distributed squad coordination over git) but is thin: one generic action verb, no concrete outputs, and no 'use when' trigger guidance. It reads more like a topic label than a capability statement with firing conditions.

Suggestions

Add an explicit 'Use when...' clause, e.g. 'Use when squads span multiple machines, VMs, CI runners, or organizations, or when a squad's files aren't on the local filesystem.'

Name the concrete outputs to raise specificity: 'Generate mesh.json from user answers, copy bundled sync scripts, and scaffold a shared git state repo.'

Include natural trigger synonyms users would say — 'distributed', 'remote squads', 'sync squads across machines' — to improve trigger_term_quality.

DimensionReasoningScore

Specificity

The description names the domain ("coordinate with squads on different machines") and one mechanism ("using git as transport"), but the only action verb is the generic "coordinate" — no concrete deliverables like mesh.json, sync scripts, or zone setup are mentioned. It sits above the vague-buzzword level but below the '1-2 concrete actions' anchor, matching 'names the domain but actions are minimal or generic'.

2 / 5

Completeness

The 'what' is reasonably clear (coordinate distributed squads via git transport), but there is no 'Use when...' clause or equivalent trigger guidance, so 'when' is only weakly implied by 'on different machines'. Per the guidelines, a missing 'Use when...' clause caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant keywords are present ("squads", "different machines", "git"), but common user phrasings are missing: "distributed", "remote squads", "sync", "multi-machine", or "cross-machine". Some relevant keywords but missing common variations and synonyms.

3 / 5

Distinctiveness Conflict Risk

"Squads on different machines using git as transport" carves a clear niche that would rarely fire for unrelated skills. Minor overlap risk remains with any sibling local-squad-coordination or general git-workflow skills that share the 'squads' and 'git' trigger terms.

4 / 5

Total

12

/

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.

Validation — 15 / 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.