CtrlK
BlogDocsLog inGet started
Tessl Logo

reflect

Learning capture system that extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes. Use after user corrections ("no", "wrong"), praise ("perfect", "exactly"), or when discovering edge cases. Complements .squad/agents/{agent}/history.md and .squad/decisions.md.

74

Quality

92%

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

85%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-organized, highly actionable skill body with clear phased workflow, explicit validation gate, and concrete output templates. The main weakness is mild redundancy where trigger examples recur across multiple sections.

Suggestions

Consolidate the trigger phrase lists: the HIGH/MED/LOW examples appear in 'Triggers', 'Phase 2', and 'When to Use' — keep one authoritative list and reference it to cut redundant tokens.

Phase 4 lists history/decision/skill targets but the file path for team decisions differs between sections (`.squad/decisions.md` vs `.squad/decisions/inbox/{agent}-{topic}.md`); pick one consistently to avoid ambiguity.

DimensionReasoningScore

Conciseness

The body is largely well-structured and avoids explaining concepts Claude already knows, but it repeats the trigger lists across 'Triggers', 'Phase 2', and 'When to Use' sections, adding tokens without new information.

2 / 3

Actionability

Provides concrete, copy-ready output templates (the ASCII reflection box), exact file paths and section targets, and worked examples with full Source/Target lines, leaving Claude with executable guidance.

3 / 3

Workflow Clarity

The four phases are clearly sequenced with an explicit confidence-threshold table acting as a validation gate, and Phase 4 enforces 'ALWAYS show changes before applying' with an approval prompt — a genuine checkpoint before persistence.

3 / 3

Progressive Disclosure

The SKILL.md is self-contained with well-organized sections and no bundle files; references to squad files are clearly signaled and one level deep, so navigation is easy for a single-file skill.

3 / 3

Total

11

/

12

Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong description that concisely states what the skill does and when to use it, with concrete natural-language triggers and a clearly bounded niche. It avoids vague fluff and third-person voice is maintained throughout.

DimensionReasoningScore

Specificity

Lists several concrete actions — 'extracts HIGH/MED/LOW confidence patterns', 'prevent repeating mistakes', and explicitly references the squad files it updates, which is a specific concrete behavior rather than vague language.

3 / 3

Completeness

Clearly answers 'what' (extracts confidence-tagged patterns from conversations) and 'when' (after corrections, praise, or edge-case discovery) with an explicit 'Use after...' trigger clause.

3 / 3

Trigger Term Quality

Quotes natural trigger phrases a user would actually say ('no', 'wrong', 'perfect', 'exactly') and ties them to invocation, giving good coverage of real trigger terms.

3 / 3

Distinctiveness Conflict Risk

The niche is clearly distinct — conversation-derived learning capture feeding squad history/decisions — with trigger terms unlikely to fire for unrelated skills, so conflict risk is low.

3 / 3

Total

12

/

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.