hindsight-architect

Expert memory architect. Understands your application, identifies where memory adds value, and produces an implementation plan with bank config, tag schema, and code.

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

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

Quality

Content

63%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 dense, well-structured, highly actionable planning skill with concrete code templates and a clear phased workflow. Its main weaknesses are repeated explanations that hurt conciseness and a monolithic structure with no bundle files to progressively disclose the product knowledge and output-format detail.

Suggestions

Move the detailed Hindsight product knowledge (facts/entities/observations, banks, tags, mental models) and the full output-format templates into reference files under references/, leaving SKILL.md as a concise overview that links one level deep.

De-duplicate the tag/identity-scoping rule and the mental-model retrieval-strategy guidance so each is stated once in its canonical section and merely referenced elsewhere.

Add an automated validation checkpoint to the workflow (e.g., verify the generated plan references every tag in the schema and every code location from the design) before declaring the plan complete.

Dimension	Reasoning	Score
Conciseness	Most content is genuinely needed Hindsight product knowledge rather than general concepts Claude knows, but the tag-as-identity-scoping rule and mental-model retrieval strategy are each repeated several times and could be tightened.	3 / 5
Actionability	Provides an executable bash preamble and concrete Python/Node retain, recall, mental-model, and client-setup code plus a specific mental-model example table, but template placeholders like {tags} and {token_budget} keep it from being fully copy-paste ready.	4 / 5
Workflow Clarity	A clear four-phase methodology with explicit gates ('Don't move to Phase 3 until…', 'When approved, move to Phase 4') and user-confirmation feedback loops; this is a planning skill so the destructive/batch cap does not apply, but checkpoints rely on user confirmation rather than automated verification.	4 / 5
Progressive Disclosure	Well-sectioned with clear headers and one signaled external pointer (the hindsight-docs skill), but as an 858-line monolith with product knowledge and output templates inlined and no reference files to offload detail, it stays one level too flat.	3 / 5
	Total	14 / 20 Passed

Description

58%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 conveys a clear, specific deliverable (an implementation plan with bank config, tag schema, and code) but lacks any explicit trigger guidance and misses natural terms a user would say, including the product name. It is distinctive enough to avoid most conflicts yet could be sharper as a discovery surface.

Suggestions

Add an explicit 'Use when...' clause naming concrete user triggers (e.g., 'Use when the user wants to add memory or persistent context to an agent, design a Hindsight memory architecture, or plan what an agent should remember across sessions').

Include the product name 'Hindsight' and natural synonyms like 'remember', 'agent memory', and 'long-term memory' to improve trigger term coverage and distinctiveness.

Mention mental models and retrieval/recall in the capability list so the scope reads as comprehensive rather than omitting two of the skill's core deliverables.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions ('Understands your application', 'identifies where memory adds value', 'produces an implementation plan with bank config, tag schema, and code'), though it omits mental models and retrieval strategy.	4 / 5
Completeness	Clearly states the 'what' (an implementation plan with bank config, tag schema, and code) but has no 'when'/'Use when' trigger clause; per guideline, a missing trigger clause caps completeness at 3.	3 / 5
Trigger Term Quality	Contains relevant terms ('memory', 'application', 'implementation plan') but misses natural variations users would say ('remember', 'agent memory', 'Hindsight', 'long-term memory') and any file extensions or synonyms.	3 / 5
Distinctiveness Conflict Risk	Hindsight-specific deliverables ('bank config', 'tag schema') carve a clear niche, though omitting the product name 'Hindsight' leaves minor overlap risk with generic memory skills.	4 / 5
	Total	14 / 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
skill_md_line_count	SKILL.md is long (859 lines); consider splitting into references/ and linking	Warning

	Total	15 / 16 Passed

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

Reviewed: ~11 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.