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.

61

Quality

73%

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 ./.squad/skills/reflect/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, actionable reflection process with clear sequencing and a pre-apply validation gate. Its main weakness is redundancy: trigger examples recur across three sections, inflating length without adding guidance.

Suggestions

Consolidate the trigger lists: keep one authoritative HIGH/MED/LOW table in the Triggers section and have Phase 2 and 'When to Use' reference it instead of restating the same examples.

Add an explicit rejection feedback loop in Phase 4 (e.g., if the user picks 'edit', revise the proposed learning and re-present for approval) to complete the validation cycle.

Consider moving the detailed usage examples and ASCII REFLECTION template into a reference file to shorten SKILL.md and improve progressive disclosure now that the body exceeds 200 lines.

DimensionReasoningScore

Conciseness

Mostly efficient prose, but the HIGH/MED/LOW trigger examples are restated three times (Triggers tables, Phase 2 detection patterns, and the closing 'When to Use' list), which is redundant padding that could be tightened; not severely verbose, so above a 2.

3 / 5

Actionability

Provides a concrete 4-phase process, specific detection patterns, a copy-ready REFLECTION output template with placeholders, a confidence-threshold table, and explicit target file paths; minor gaps (placeholders vs. fully filled examples) keep it just below a 5.

4 / 5

Workflow Clarity

Four phases are clearly sequenced with an explicit validation checkpoint ('ALWAYS show changes before applying') and a user approval gate ('Apply changes? [Y/n/edit]') before persisting; lacks an explicit revise-and-re-propose feedback loop on rejection, so not a 5.

4 / 5

Progressive Disclosure

No bundle files exist and all content is inline, but the body is well-organized into clearly signaled sections (Integration, Triggers, Process, Examples, When to Use, See Also) with no nested references; the cross-section repetition is a minor organization gap preventing a 5.

4 / 5

Total

15

/

20

Passed

Description

78%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.

A strong description that clearly states both purpose and explicit usage triggers with natural user phrases. It is distinct and well-targeted, with only minor room to broaden trigger synonyms and enumerate more concrete actions.

DimensionReasoningScore

Specificity

Names the domain ('Learning capture system') and a concrete action ('extracts HIGH/MED/LOW confidence patterns from conversations to prevent repeating mistakes'), but does not enumerate multiple specific actions; the core verb ('extracts patterns') stays somewhat abstract, matching the '1-2 concrete actions, not comprehensive' anchor.

3 / 5

Completeness

Explicitly answers both 'what' (learning capture system that extracts confidence-tagged patterns to prevent repeating mistakes) and 'when' ('Use after user corrections..., praise..., or when discovering edge cases') with concrete trigger phrases, matching the top anchor.

5 / 5

Trigger Term Quality

Quotes natural trigger phrases users actually say ('no', 'wrong', 'perfect', 'exactly') plus 'edge cases', giving good keyword coverage; falls short of a 5 because it lacks synonyms and file-extension-style breadth.

4 / 5

Distinctiveness Conflict Risk

Carves a fairly distinct reflection/learning-capture niche anchored to Squad-specific paths (.squad/agents/{agent}/history.md, .squad/decisions.md); minor overlap risk with general memory/history skills keeps it just below a 5.

4 / 5

Total

16

/

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.

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.