distributed-mesh

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

Quality

58%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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 content is a strong, deterministic setup guide with concrete commands and templates and a clear 6-step workflow, but it is weakened by repeated scope/anti-pattern restatements, missing validation checkpoints, and—most importantly—dangling references to bundled resources (sync scripts, mesh.json.example) that are not actually present in the skill bundle.

Suggestions

Ship the referenced bundle files (sync-mesh.sh, sync-mesh.ps1, mesh.json.example) under the skill directory, or stop instructing Claude to copy files that do not exist.

Consolidate the scope/anti-pattern guidance into one section (e.g. keep SCOPE and remove the duplicated lists from Step 6 STOP and Anti-Patterns) to reduce redundancy.

Add a validation checkpoint after Step 2 (e.g. confirm mesh.json is valid JSON and every squad has its required zone fields) and after Step 4 (confirm --init created the expected squad directories) before declaring completion.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and assumes Claude's competence, but the scope/anti-pattern message ('do not generate sync scripts — copy them; no app code, no tests, no daemons') is restated across SCOPE, Step 6 STOP, and the Anti-Patterns section, which is noticeable redundancy rather than the 'minor instances' of a score-4.	3 / 5
Actionability	Provides concrete, copy-paste-ready guidance: an explicit mesh.json schema, exact source/destination copy paths, `bash sync-mesh.sh --init`, and a filled-in decision-entry template; held back from 5 because the referenced bundle files (sync-mesh.sh/.ps1, mesh.json.example) do not exist, so the COPY and template steps cannot actually be executed as written.	4 / 5
Workflow Clarity	The AGENT WORKFLOW lays out six explicitly sequenced steps with exact commands, a skip condition for Step 4, and an explicit STOP at Step 6; it does not reach 5 because there are no validation/feedback checkpoints after generating mesh.json or running --init (e.g. verify the file is well-formed or that init succeeded).	4 / 5
Progressive Disclosure	The body is well-sectioned (SCOPE, Context, Patterns, Examples, AGENT WORKFLOW, Anti-Patterns) and references are explicitly signaled, but the referenced bundle files (mesh.json.example, sync-mesh.sh, sync-mesh.ps1 under .copilot/skills/distributed-mesh/) are absent from the actual bundle, and the mesh.json schema is both inlined and referenced as a separate file, so the skill cannot deliver its claimed progressive-disclosure structure.	3 / 5
	Total	14 / 20 Passed

Description

53%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 clearly states the skill's purpose and transport mechanism in third person, but lacks an explicit 'Use when...' trigger clause and relies on a generic action verb, capping completeness and trigger-term quality at mid-range.

Suggestions

Add an explicit 'Use when...' clause naming concrete triggers, e.g. 'Use when squads span multiple machines, VMs, CI runners, or organizations and remote squad files must be materialized locally.'

Replace the generic verb 'coordinate' with specific actions the skill performs, such as 'configure a mesh topology and install git/curl sync scripts'.

Include natural user-facing synonyms ('distributed squads', 'cross-machine', 'remote squad context') alongside the framework jargon to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ('coordinate with squads on different machines') plus one concrete mechanism ('using git as transport'), but the only action verb ('coordinate') is generic; fits the 'names domain and 1-2 concrete actions, not comprehensive' anchor better than the score-2 'minimal/generic actions' anchor.	3 / 5
Completeness	Provides a clear 'what' (coordinate squads across machines via git) but no 'Use when...' trigger clause; per the rubric, a missing explicit trigger clause caps completeness at 3, so it does not reach the score-4 'has both what and when' anchor.	3 / 5
Trigger Term Quality	Relevant keywords are present ('squads', 'different machines', 'git', 'transport'), but 'squads' and 'git as transport' are framework-specific jargon and common user-facing synonyms/variations are missing, matching the 'some relevant keywords but missing common variations' anchor.	3 / 5
Distinctiveness Conflict Risk	The combination of 'squads on different machines' + 'git as transport' carves a fairly distinct niche with only minor overlap risk against other squad-coordination skills; not a score-5 because the broad verb 'coordinate' leaves some ambiguity versus sibling squad skills.	4 / 5
	Total	13 / 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/distributed-mesh/SKILL.md
Commit: 9587fcd

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.