hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)

Quality

81%

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

Quality

Content

85%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 delivers concrete, executable CLI commands with a clear setup-validation flow and well-organized self-contained sections. It is slightly held back by inferable bulleted lists and minor repetition between the pipeline explanation and best practices.

Suggestions

Tighten the 'When to Store' and 'When to Recall' bulleted lists to non-obvious examples only, removing items Claude can infer (e.g., generic 'Communication preferences').

De-duplicate the rich-context guidance: keep the rationale in 'How Hindsight Works' and reduce Best Practices point 2 to a one-line cross-reference rather than restating it.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with novel tool-pipeline info, but the bulleted preference/learning lists are partly inferable and 'Pass rich context' in Best Practices repeats the How Hindsight Works section; could be tightened rather than a lean 3.	2 / 3
Actionability	Fully executable `uvx hindsight-embed memory retain/recall/reflect` commands with real examples and `--context` flags, copy-paste ready; not a 2 since there is no pseudocode or missing detail.	3 / 3
Workflow Clarity	Setup has an explicit validation plus feedback loop (check daemon status, if it fails run configure), and the store/recall/reflect commands are unambiguous for a simple skill; not a 2 because a validation checkpoint is present.	3 / 3
Progressive Disclosure	No bundle files exist; the body is self-contained and well-sectioned with no nested references and easy navigation, fitting the well-organized-sections anchor; not a 2 since there is no inline content that should be split out.	3 / 3
	Total	11 / 12 Passed

Description

77%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 cleanly states what the skill stores and gives an explicit when-to-use trigger, with concrete action categories. Trigger terms are somewhat generic and the memory niche could overlap with similar skills, holding it back from the top band.

Suggestions

Add concrete user-sayable trigger terms (e.g., 'preferences', 'what worked last time', 'past learnings') alongside 'remember what works' to improve trigger coverage.

Sharpen distinctiveness by naming the hindsight memory store or contrasting with one-off notes, so it is less likely to conflict with generic memory skills.

Dimension	Reasoning	Score
Specificity	Lists three concrete actions — 'Store user preferences, learnings from tasks, and procedure outcomes' — matching the multi-action anchor; not the level below which only names a domain.	3 / 3
Completeness	Answers both what (store preferences/learnings/procedure outcomes) and when via an explicit 'Use to...before new tasks' trigger clause; not a 2 since the when is explicit rather than implied.	3 / 3
Trigger Term Quality	'remember what works' and 'recall context before new tasks' are natural-ish but generic and missing common variations a user would say; not a 3 which requires broad coverage of concrete user-sayable terms.	2 / 3
Distinctiveness Conflict Risk	The preferences/learnings/procedures niche is somewhat specific, but 'remember what works and recall context' could overlap with other memory-style skills; not a clear-enough niche for a 3.	2 / 3
	Total	10 / 12 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vectorize-io/hindsight
Path: skills/hindsight-local/SKILL.md
Commit: ed120a2

Reviewed: 7 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.