agent-patterns

Execute this skill should be used when the user asks about "SPAWN REQUEST format", "agent reports", "agent coordination", "parallel agents", "report format", "agent communication", or needs to understand how agents coordinate within the sprint system. Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.

Quality

63%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/community/sprint/skills/agent-patterns/SKILL.md

Quality

Content

77%Weight 40%Scale 1-3

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 copy-paste-ready blocks, a clear sequenced workflow, and strong error-recovery guidance. The main gaps are mild redundancy between Instructions and Examples and two unreferenced bundle files that weaken navigation.

Suggestions

De-duplicate the SPAWN REQUEST/AGENT REPORT blocks: keep the canonical format in Instructions and point Examples to references/examples.md rather than restating them.

Link references/errors.md and references/examples.md from the body (e.g. in Error Handling and Examples sections) so all bundle files are navigable.

Trim any restated scope-partitioning guidance to keep the Instructions section token-lean.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean with concrete blocks and no concept explanations, but the Examples section repeats the SPAWN REQUEST and AGENT REPORT formats already shown in Instructions, so it 'could be tightened'.	2 / 3
Actionability	It supplies fully copy-paste-ready SPAWN REQUEST and AGENT REPORT blocks with named fields plus a concrete parallel-coordination example using Run After, matching 'Fully executable code/commands; specific examples; copy-paste ready'.	3 / 3
Workflow Clarity	Instructions form a clear numbered sequence (spawn -> scope -> collect reports -> partition parallel work -> feed back to architect) with an explicit error-handling table and a feedback loop (architect iterates/advances, orchestrator pauses after 5 iterations), matching 'Clear sequence with explicit validation steps; feedback loops for error recovery'.	3 / 3
Progressive Disclosure	Sections are well-organized and it signals one real one-level-deep reference (ui-test-report.md), but references/errors.md and references/examples.md are orphaned from the body and the inline Examples could live in examples.md, matching 'Some structure but could be better organized'.	2 / 3
	Total	10 / 12 Passed

Description

50%Weight 40%Scale 1-3

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 surfaces a clear niche and several explicit trigger phrases, but it lacks concrete action verbs and pads the 'when' guidance with generic filler. Tightening it to lead with what the skill does and dropping boilerplate would lift specificity and completeness.

Suggestions

Rewrite the opening to lead with concrete actions, e.g. 'Spawns implementation and testing agents, partitions parallel work, and collects structured agent reports for the sprint orchestrator.'

Replace the generic filler 'Use when appropriate context detected. Trigger with relevant phrases based on skill purpose.' with the concrete trigger list only, and keep a single explicit 'Use when...' clause.

Add a couple of natural user phrasings (e.g. 'coordinate agents', 'agent task handoff') alongside the jargon to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain ("how agents coordinate within the sprint system") and trigger phrases but lists no concrete actions the skill performs (spawning agents, partitioning work, collecting reports); it stops at 'Names domain and some actions, but not comprehensive'.	2 / 3
Completeness	It states a 'what' and includes a 'Use when...' clause with explicit trigger phrases, but the 'when' is diluted by generic filler ("Use when appropriate context detected", "Trigger with relevant phrases based on skill purpose"), keeping it at the 'when is only implied/weak' boundary rather than a clear 3.	2 / 3
Trigger Term Quality	Phrases like "agent reports", "agent coordination", "parallel agents" are reasonable, but "SPAWN REQUEST format" is internal jargon and common natural variations are missing, matching 'Some relevant keywords but missing common variations'.	2 / 3
Distinctiveness Conflict Risk	The multi-agent sprint coordination niche and "SPAWN REQUEST format" triggers are fairly distinct, yet the skill could still overlap with a general sprint-workflow skill, matching 'Somewhat specific but could still overlap with similar skills'.	2 / 3
	Total	8 / 12 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: jeremylongshore/claude-code-plugins-plus-skills
Path: plugins/community/sprint/skills/agent-patterns/SKILL.md
Commit: c4eafaf

Reviewed: 5 days 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.