hindsight-docs

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

Quality

67%

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

Fix and improve this skill with Tessl

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

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 is a strong, well-structured navigation skill: concrete executable search patterns, a clear sequenced workflow with an entry point, and clean progressive disclosure into verified reference files. The only weak spot is minor conciseness redundancy between the directory tree and the 'Start Here' section.

Dimension	Reasoning	Score
Conciseness	The body is mostly lean and assumes Claude's competence, but it carries minor redundancy: best-practices.md appears both in the directory tree and in a dedicated 'Start Here' section, and the opening line restates the description.	2 / 3
Actionability	Provides concrete, copy-paste-ready tool guidance: specific Glob patterns, Grep patterns with example search strings ('disposition', 'POST /v1'), and explicit Read file paths — all directly executable.	3 / 3
Workflow Clarity	Presents a clear, sequenced navigation workflow (Glob to find files, Grep to search content, Read for full docs) with an explicit 'START HERE' entry point; as a non-destructive documentation skill it does not need validation checkpoints.	3 / 3
Progressive Disclosure	SKILL.md is a lean overview pointing into a well-organized references tree with a per-file-commented directory listing, a 'START HERE' marker, and three search strategies; referenced paths (python.md, configuration.md, retain.md, litellm.md) all exist and nesting is shallow.	3 / 3
	Total	11 / 12 Passed

Description

50%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 clearly identifies the named product and topics but relies on passive documentation verbs and purpose-oriented 'Use this to' guidance rather than natural user trigger terms or concrete situational triggers. It answers what and a form of when, but not as sharply as the top anchor.

Suggestions

Rewrite as concrete actions a user would request, e.g. 'Retain, recall, and reflect on agent memories using Hindsight' instead of generic 'documentation for'/'learn about' verbs.

Add natural user trigger phrases to the description: 'Use when the user mentions Hindsight, agent memory, retain/recall/reflect, memory banks, or dispositions.'

Replace generic topic words (architecture, APIs, configuration, best practices) with the distinctive Hindsight vocabulary (memory banks, dispositions, mental models, retrieval strategies) to reduce overlap with other documentation skills.

Dimension	Reasoning	Score
Specificity	Names the Hindsight domain and lists multiple specific content areas ('architecture, APIs, configuration, and best practices') but the verbs are uniform/passive ('documentation for', 'learn about') rather than multiple distinct concrete actions, so it stops short of the level-3 bar.	2 / 3
Completeness	States both what ('Complete Hindsight documentation') and an explicit 'Use this to learn about...' clause, but the when is framed as purpose rather than concrete triggering situations, which the level-3 anchor requires.	2 / 3
Trigger Term Quality	Includes relevant domain keywords but omits the natural terms a user would actually say when needing this skill ('memory', 'recall', 'retain', 'memory banks'), so coverage of natural variations is incomplete.	2 / 3
Distinctiveness Conflict Risk	The named product (Hindsight) gives it a distinct niche unlikely to broadly conflict, but the trigger words (architecture, APIs, configuration, best practices) are generic and could overlap with other documentation skills.	2 / 3
	Total	8 / 12 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: 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.