CtrlK
BlogDocsLog inGet started
Tessl Logo

iterative-retrieval

Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation. Use when spawning sub-agents to complete scoped work.

67

Quality

81%

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

SKILL.md
Quality
Evals
Security

Quality

Content

77%

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 clear workflows, concrete templates, and strong validation feedback loops. Its weaknesses are mild verbosity from cross-section restatement and a monolithic single-file structure that forgoes progressive disclosure.

Suggestions

Trim overlap between the prose intro, Rules, and Anti-Patterns sections so each point appears once in its most authoritative location.

Consider splitting the spawn template or the good/bad examples into a referenced bundle file to reduce inline length and improve navigability.

DimensionReasoningScore

Conciseness

Mostly efficient and protocol-focused without re-explaining basics, but the prose intro and the Anti-Patterns section restate points already covered by the template, checklist, and rules, so it could be tightened.

2 / 3

Actionability

Provides a copy-paste spawn template with fill-in sections, a concrete `gh issue list --search` command, checkbox checklists, and contrasting good/bad examples — fully actionable.

3 / 3

Workflow Clarity

The 3-cycle table sequences the process clearly, with explicit coordinator validation after each cycle and a retry-then-escalate feedback loop plus checklists for recovery.

3 / 3

Progressive Disclosure

The body is well-sectioned but is a single ~157-line monolithic file with no bundle references; the spawn template, checklists, and examples are inlined where a one-level split could aid navigation.

2 / 3

Total

10

/

12

Passed

Description

85%

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 is specific, complete, and distinctive, clearly stating both the protocol's mechanics and its trigger condition. Its main weakness is trigger-term breadth, relying on a single 'spawning sub-agents' phrasing rather than covering the natural language variations users would actually say.

Suggestions

Broaden trigger terms to include phrases users naturally say, e.g. 'Use when delegating work to sub-agents, coordinating agent handoffs, or spawning scoped sub-tasks'.

Consider naming the coordinator-validation outcome more concretely, e.g. 'validates agent output before closing an issue'.

DimensionReasoningScore

Specificity

Names concrete mechanisms — 'Max-3-cycle protocol', 'WHY context', and 'coordinator validation' — listing multiple specific actions rather than vague domain language.

3 / 3

Completeness

Explicitly answers both what ('Max-3-cycle protocol for agent sub-tasks with WHY context and coordinator validation') and when ('Use when spawning sub-agents to complete scoped work').

3 / 3

Trigger Term Quality

Includes one natural trigger ('Use when spawning sub-agents') but misses common variations a user might actually say, such as 'delegating work', 'agent handoffs', or 'coordinating agents'.

2 / 3

Distinctiveness Conflict Risk

Occupies a clear niche (structured sub-agent spawning protocol) with distinct triggers unlikely to fire for unrelated skills.

3 / 3

Total

11

/

12

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.

Validation15 / 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.