hindsight-docs

Complete Hindsight documentation for AI agents. Use this to learn about Hindsight architecture, APIs, configuration, and best practices.

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Failed to scan

The risk profile of this skill

Fix and improve this skill with Tessl

tessl review fix ./skills/hindsight-docs/SKILL.md

Quality

Content

75%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 documentation-index skill that stays lean and gives concrete navigation patterns (Glob/Grep/Read) into a clearly diagrammed reference tree. It earns high marks for progressive disclosure and actionability, with only mild redundancy and minor two-level nesting keeping it from the top anchor.

Suggestions

Collapse the redundancy between the 'Documentation Structure' tree and the 'How to Find Documentation' pattern block into one consolidated navigation section to tighten conciseness.

Add one short worked example showing a full lookup (e.g. 'To configure retrieval: read references/best-practices.md, then references/developer/configuration.md') to lift actionability toward 5.

Flatten or explicitly annotate the two-level integrations/api subdirectories (e.g. note that references/sdks/integrations/*.md are per-framework guides) so the reference tree reads as cleanly one-level-deep.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence — it indexes docs rather than restating them — with only minor redundancy between the 'Documentation Structure' tree and the 'How to Find Documentation' pattern lists; not a 5 because those two sections overlap somewhat.	4 / 5
Actionability	Provides concrete, copy-paste-ready Glob/Grep/Read patterns with real paths and search strings (e.g. 'references/developer/api/*.md', pattern: 'HINDSIGHT_API_'); minor gaps keep it from 5, such as no worked end-to-end lookup example.	4 / 5
Workflow Clarity	A clear three-step navigation sequence (Find by pattern → Search content → Read full docs) with a 'Start Here: Best Practices' entry point; no validation checkpoints are needed for read-only doc lookup, but the steps are guidance rather than a rigorous sequenced procedure, so it sits at 4.	4 / 5
Progressive Disclosure	SKILL.md is an overview pointing into a well-organized, clearly diagrammed references/ tree with a 'START HERE' marker; not a 5 because several areas nest two levels deep (references/sdks/integrations/, references/developer/api/) rather than the ideal one-level-deep, though nesting is explicitly signaled and navigable.	4 / 5
	Total	16 / 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 solid, third-person description that names the product and several concrete coverage areas with an explicit 'Use this to learn about' trigger clause. It is distinct and unlikely to conflict, but the trigger phrasing could be more natural and explicit about user utterances.

Suggestions

Add concrete user-trigger phrasing to the when-clause, e.g. 'Use when the user asks about Hindsight, mentions memory banks/retain/recall, or needs to configure the Hindsight API.'

Include natural synonyms and file/extension tokens (e.g. 'Hindsight API', 'openapi.json', 'memory bank') to broaden trigger-term coverage.

Tighten the 'what' to lead with the most distinctive capability (e.g. 'Biomimetic memory system for AI agents') so the niche is immediately clear.

Dimension	Reasoning	Score
Specificity	Names the domain ('Complete Hindsight documentation') and lists several concrete coverage areas — 'architecture, APIs, configuration, and best practices' — with only minor gaps, matching the 'lists several specific actions' anchor; not a 5 because the items are learnable topics rather than a comprehensive set of concrete actions.	4 / 5
Completeness	It answers 'what' ('Complete Hindsight documentation...') and 'when' ('Use this to learn about...'), but the when-clause describes learning tasks rather than concrete user trigger phrases like 'Use when the user mentions X', so it falls short of a 5.	4 / 5
Trigger Term Quality	Good keyword coverage with natural phrases a user would say ('Hindsight architecture', 'APIs', 'configuration', 'best practices'), but it lacks synonyms and the explicit '.json'/file-form tokens that would push it to 5.	4 / 5
Distinctiveness Conflict Risk	The named product 'Hindsight' with its specific scope (architecture, APIs, configuration) carves a clear niche with minimal overlap risk against other skills.	5 / 5
	Total	17 / 20 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
referenced_paths_exist	Referenced path issues: 6 deeper-than-1-level	Warning

	Total	15 / 16 Passed

Repository: vectorize-io/hindsight
Path: skills/hindsight-docs/SKILL.md
Commit: d2e8fa7

Reviewed: ~12 hours 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.