CtrlK
BlogDocsLog inGet started
Tessl Logo

agent-collaboration

Standard collaboration patterns for all squad agents — worktree awareness, decisions, cross-agent communication

60

Quality

70%

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 ./.copilot/skills/agent-collaboration/SKILL.md

The canonical home for this skill is agent-collaboration in bradygaster/squad

SKILL.md
Quality
Evals
Security

Quality

Content

86%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 strong example of a lean, actionable instruction-only skill: exact paths, a copy-paste decision format, concrete fallbacks, and explicit anti-patterns with no padding. The only trimmable content is the Context section's justification arithmetic, and the workflows are unambiguous though without validation checkpoints.

DimensionReasoningScore

Conciseness

The ~35-line body is lean and assumes competence, giving exact paths and formats with no concept explanations. Only the Context section's byte-arithmetic rationale ('~300 bytes × 18 agents = ~5.4KB of redundant context') could be trimmed, so it sits between 'efficient' and 'lean and efficient; every token earns its place'.

4 / 5

Actionability

Fully executable guidance for an instruction-only skill: the exact drop-box path '.squad/decisions/inbox/{your-name}-{brief-slug}.md', a copy-paste decision format block, a concrete fallback command 'git rev-parse --show-toplevel', and explicit anti-patterns. As an instruction-only skill the absence of code is not penalized since the guidance is directly actionable.

5 / 5

Workflow Clarity

Four independent single-step patterns, each unambiguous with an explicit fallback for TEAM ROOT resolution; no destructive or batch operations requiring validation. Not 5 because there is no unifying sequence across the patterns and no post-write verification checkpoint for the decision-recording workflow.

4 / 5

Progressive Disclosure

Under 50 lines, no external bundle files needed, and a clean section structure (Context, four Pattern subsections, Anti-Patterns) — the simple-skill case where well-organized sections alone merit a 5. All referenced paths (.squad/decisions, history.md, charters) are contextual pointers, not file references requiring navigation.

5 / 5

Total

18

/

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 names a distinct niche and its three sub-topics but never converts them into concrete actions or a usage trigger. It reads as a table-of-contents rather than a capability statement, capping completeness and trigger quality at the midpoint.

Suggestions

Add a 'Use when...' clause, e.g. 'Use when spawned as a squad agent, when recording a decision that affects teammates, or when you need another agent's input', to explicitly answer the 'when' question.

Convert noun-phrase topics into concrete actions, e.g. 'Records decisions to the .squad/decisions/inbox/ drop-box, resolves paths via TEAM ROOT, and requests teammate input through the coordinator'.

Include natural trigger keywords and synonyms users/agents would actually say, such as 'team decisions', 'request help', 'reviewer rejection', or 'spawn prompt', to improve trigger term coverage.

DimensionReasoningScore

Specificity

Names the domain ('collaboration patterns for all squad agents') and lists three topic areas ('worktree awareness, decisions, cross-agent communication'), but these are noun-phrase topics rather than concrete actions, matching the 'names domain and 1-2 concrete actions but not comprehensive' anchor. Not 4 because it never states what the skill actually does with those topics.

3 / 5

Completeness

Has a clear 'what' (standard patterns for three named areas) but no 'when' — there is no 'Use when...' clause or equivalent trigger guidance, which per the judging guidelines caps completeness at 3. Not 4 because the 'when' is entirely absent rather than just weakly explicit.

3 / 5

Trigger Term Quality

Contains some relevant keywords ('collaboration patterns', 'worktree awareness', 'cross-agent communication') but misses common variations and natural user phrasings like 'team coordination', 'agent handoff', or 'request help'. Not 4 because coverage of natural trigger terms is thin, not 2 because the terms present are domain-relevant rather than generic.

3 / 5

Distinctiveness Conflict Risk

'Standard collaboration patterns for all squad agents' carves out a fairly distinct niche with named sub-areas, unlikely to trigger for unrelated skills. Not 5 because 'decisions' and 'cross-agent communication' are broad terms that could overlap with other team-workflow or decision-making skills.

4 / 5

Total

13

/

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.