hindsight-docs

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

Quality

72%

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

78%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.

The body is a well-structured, lean navigation guide that uses concrete tool invocations and excellent progressive disclosure to route Claude to a real references bundle, with only minor redundancy and no destructive-operation validation needs.

Dimension	Reasoning	Score
Conciseness	The body is lean — a directory tree, glob/grep patterns, a key-concepts list, and short notes — assuming Claude's competence, with only minor redundancy in the Notes section echoing Key Concepts.	4 / 5
Actionability	Provides concrete, copy-paste-ready tool guidance (Glob patterns, Grep pattern/path syntax, explicit Read paths), which is actionable for a navigation skill, though it lacks executable Hindsight usage code.	4 / 5
Workflow Clarity	'How to Find Documentation' is a clear 3-step sequenced workflow (Glob → Grep → Read) appropriate for read-only lookup; no validation checkpoints are needed for non-destructive lookups, leaving it just short of anchor 5.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview pointing to a real, well-organized references/ tree one level deep, with an explicit directory map, a 'START HERE' pointer, and clearly signaled navigation.	5 / 5
	Total	17 / 20 Passed

Description

66%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.

The description is clearly scoped to a distinct named product and answers both what and when, but its triggers are topic-oriented rather than natural user phrases and its verbs are passive consumption rather than concrete actions.

Suggestions

Replace passive 'learn about' with concrete skill verbs (e.g., 'Look up Hindsight architecture, API endpoints, and configuration options') to raise specificity.

Reframe the 'when' clause around phrases a user would actually say (e.g., 'Use when the user asks about Hindsight, its API, memory banks, or SDK integration').

Add natural synonyms and identifiers users mention (e.g., 'Hindsight API', 'Hindsight memory', 'retain/recall/reflect') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Names the domain and lists several coverage areas ('architecture, APIs, configuration, and best practices'), but the verb is passive ('learn about') and these are topics rather than concrete actions like extract or merge, so it sits below the comprehensive anchor 4.	3 / 5
Completeness	Explicitly answers both what ('Complete Hindsight documentation for AI agents') and when ('Use this to learn about...'), but the trigger lists topics rather than user-utterance phrases, so it falls short of anchor 5.	4 / 5
Trigger Term Quality	Includes relevant domain keywords ('Hindsight', 'architecture', 'APIs', 'configuration') but they are technical terms a user would not naturally utter as a trigger, and synonyms and variations are missing.	3 / 5
Distinctiveness Conflict Risk	Tied to the unique proper noun 'Hindsight', giving it a clear niche with distinct triggers and minimal conflict risk with other skills.	5 / 5
	Total	15 / 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: 9c7f6c6

Reviewed: 1 day 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.