Tessl • The management layer for AI agent skills

SkillPublic

hindsight-docs

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

Quality

78%

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

82%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-executed progressive-disclosure index for a large documentation bundle — concrete search/read guidance, a designated starting point, and verified reference paths. The only issues are minor: slight redundancy between sections, a missing directory category in the tree, and a dangling script reference.

Suggestions

Add references/cloud-enterprise/ to the directory tree so those three files (enterprise.md, hindsight-cloud.md, overview.md) are discoverable via the index.

Remove or qualify the "Run ./scripts/generate-docs-skill.sh" note — that script is not part of the skill bundle, so the reference is dangling.

Trim duplication: drop the "When to Use This Skill" list (the description already carries it) and state the best-practices-first rule once instead of in both the tree comment and its own section.

Dimension	Reasoning	Score
Conciseness	The body is a lean navigation index with concrete glob/grep examples, but the "When to Use This Skill" section duplicates the description's job, "Start Here" repeats the "# START HERE" marker from the tree, and document_id is explained in both Key Concepts and Notes.	4 / 5
Actionability	Fully executable guidance: copy-paste-ready glob patterns, grep patterns with example search strings ("disposition", "HINDSIGHT_API_", "POST /v1"), and exact file paths to Read — exactly what an agent needs to navigate a ~140-file doc bundle.	5 / 5
Workflow Clarity	A clear numbered sequence (Glob → Grep → Read) with an explicit "Start Here: Best Practices" entry point; no validation steps are needed since there are no destructive or batch operations. The entry-point guidance appears after the find/search methods rather than leading them, a minor sequencing gap.	4 / 5
Progressive Disclosure	Scored against the actual bundle: SKILL.md is a lean overview pointing to real one-level-deep reference files that all exist. Two minor gaps keep it from a 5: the structure tree omits the entire references/cloud-enterprise/ directory, and the body cites ./scripts/generate-docs-skill.sh which does not exist in the bundle.	4 / 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.

A distinct, correctly scoped description that answers both what and when, but it stays at the level of topic areas rather than concrete capabilities. Adding the memory-system nature of Hindsight and natural trigger phrases (memory banks, retain/recall, SDKs, deployment) would sharpen both specificity and trigger coverage.

Suggestions

State what Hindsight actually is (a biomimetic memory system) so the description triggers when users mention agent memory, not just the product name.

Replace the generic "learn about" with concrete capabilities: retain/recall/reflect operations, configuring memory banks and dispositions, deploying the API server, and integrating Python/Node.js SDKs.

Add scenario-based trigger phrasing, e.g. "Use when working with Hindsight, memory banks, retain/recall/reflect, or deploying/integrating the Hindsight API."

Dimension	Reasoning	Score
Specificity	Names the domain ("Complete Hindsight documentation") and lists topic areas ("architecture, APIs, configuration, and best practices"), but the only action is the generic "learn about" — no concrete operations like retain/recall, deployment, or SDK usage appear.	3 / 5
Completeness	Both "what" ("Complete Hindsight documentation for AI agents") and "when" ("Use this to learn about...") are explicitly present, but the trigger is a topic list rather than scenario-based phrasing (no "Use when working with..." or user-mention triggers), so it falls short of a 5.	4 / 5
Trigger Term Quality	Includes the distinct product name plus a few relevant keywords ("APIs", "configuration", "best practices"), but misses the natural phrases users would say for a memory system — "memory", "memory banks", "retain/recall", "SDK", "deploy".	3 / 5
Distinctiveness Conflict Risk	The description hinges on the specific product name "Hindsight", giving it a clear niche with distinct triggers and minimal risk of firing for unrelated 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
Revision: b4a0da1

Reviewed: 5 days ago

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.

hindsight-docs

Table of Contents

Is this your skill?