Tessl • The package manager for agent skills

Blog Docs Log inGet started

SkillPublic

team-coordination

Multi-person projects - shared state, todo claiming, handoffs

Quality

68%

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 ./skills/team-coordination/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.

A highly actionable, well-sequenced coordination skill whose templates and checklists give Claude exact artifacts to produce, undermined by a monolithic single-file layout and duplicated/padded content that inflates token cost. Weakest on progressive disclosure (no reference files despite template-heavy content) and conciseness (repeated checklists and decorative ASCII blocks).

Suggestions

Move the full worked templates (state.md, contributors.md, handoff, standup) into references/ files and keep only field summaries in SKILL.md, e.g. "**Handoff template**: See [HANDOFF.md](references/HANDOFF.md)".

Deduplicate the start/end session checklists — keep one canonical version (the final Checklist section) and delete the ASCII-box repeats in Workflow.

Delete the "Core Philosophy" ASCII box and replace the fake-team worked examples with lean skeleton templates, and fix the pre-push hook to use `md5sum` (or detect `md5` vs `md5sum`).

Dimension	Reasoning	Score
Conciseness	The templates and checklists are the genuine payload, but the ASCII "Core Philosophy" box, the fully-populated fake-team examples (e.g. the working-hours overlap chart), and the start/end checklists duplicated twice (as ASCII boxes in Workflow and again in the final Checklist section) are padding that could be trimmed.	3 / 5
Actionability	Concrete file paths, copy-paste-ready markdown templates, exact git commands, and an executable pre-push hook give mostly executable guidance; minor gaps remain — the hook uses `md5` (not `md5sum` on Linux) and "Run /check-contributors" references a command that may not resolve.	4 / 5
Workflow Clarity	Start-session, claim, during-work, and end-session sequences are clearly ordered with checklists, and the pre-push state-drift check plus pull-resolve-push guidance act as checkpoints; not a 5 because the drift check is warning-only with no explicit re-check loop.	4 / 5
Progressive Disclosure	The body is well-sectioned and easy to navigate, but it is a ~478-line monolith with no bundle files at all — full templates (state.md, contributors.md, handoff, standup) that clearly belong in separate reference files are inlined in SKILL.md.	3 / 5
	Total	14 / 20 Passed

Description

58%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 names a distinct niche with several concrete capabilities, but it lacks any explicit "when to use" trigger clause and misses the natural vocabulary (team, collaboration, multiple developers) users would most likely say. It sits noticeably above the vague-baseline but well below the exemplar descriptions that combine full capability lists with explicit trigger phrases.

Suggestions

Add an explicit trigger clause, e.g. "Use when multiple developers (or multiple Claude sessions) are working on the same repo or when the user mentions team coordination, collaboration, or claiming todos."

Broaden natural trigger vocabulary to include synonyms users actually say: "team", "collaborate", "shared codebase", "merge conflicts", "working together".

Round out the capability list to match what the skill actually covers — decision syncing, conflict prevention, and session awareness are in the body but absent from the description.

Dimension	Reasoning	Score
Specificity	"shared state, todo claiming, handoffs" lists several concrete capabilities in the multi-person domain, but coverage is incomplete — the body also covers decision syncing, conflict prevention, and session awareness, which the description omits.	4 / 5
Completeness	The "what" is clear (shared state, todo claiming, handoffs) but there is no "Use when..." clause or equivalent trigger guidance in the description field, which caps completeness at 3 per the judging guidelines.	3 / 5
Trigger Term Quality	"Multi-person projects", "todo claiming", and "handoffs" are relevant keywords, but common natural phrasings users would say — "team", "collaboration", "multiple developers", "same repo", "merge conflicts" — are missing.	3 / 5
Distinctiveness Conflict Risk	"todo claiming" and "handoffs" are distinctive triggers for a clear team-coordination niche, but "shared state" and "multi-person projects" are broad enough to overlap with generic state- or project-management skills.	4 / 5
	Total	14 / 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: alinaqi/maggy
Path: skills/team-coordination/SKILL.md
Revision: 55aabe2

Reviewed: 26 days ago

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.

team-coordination

Table of Contents

Is this your skill?