hindsight-local

Store user preferences, learnings from tasks, and procedure outcomes. Use to remember what works and recall context before new tasks. (user)

Quality

79%

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-local/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.

The body is highly actionable with copy-paste-ready commands and a clear setup-then-use workflow supported by explicit when-to-store/recall guidance. Its weakest point is conciseness, where the internal-pipeline explanation and partially redundant best-practices section could be trimmed.

Suggestions

Trim or move the 'How Hindsight Works' internal-pipeline explanation (extracts facts, identifies entities, builds relationships, generates embeddings) since Claude mainly needs the behavioral rule 'pass rich context, the server extracts facts' rather than the pipeline internals.

Consolidate 'Best Practices' with the 'When to Store'/'When to Recall' sections to remove the partial restatement of store-immediately, pass-rich-context, and recall-first guidance.

Add a brief note on expected recall output or how to handle empty/no-match recall results, so the recall workflow has a small feedback checkpoint for the common edge case.

Dimension	Reasoning	Score
Conciseness	Mostly efficient command examples, but the 'How Hindsight Works' pipeline explanation and 'Best Practices' partially restate earlier sections, fitting 'mostly efficient but includes some unnecessary explanation or could be tightened' rather than the lean anchor of 4.	3 / 5
Actionability	Provides fully executable, copy-paste-ready `uvx hindsight-embed` commands for retain/recall/reflect with realistic example content and the `--context` flag, covering the common cases as the exemplary anchor requires.	5 / 5
Workflow Clarity	Clear setup-first sequence with an explicit validation checkpoint ('If this fails or shows not configured, run setup') and well-organized when-to-store/recall triggers, but lacks deeper feedback loops beyond setup, fitting 'clear sequence with most checkpoints; minor validation gaps' rather than 5.	4 / 5
Progressive Disclosure	Well-organized into clearly labeled sections (Setup, How it Works, Commands, When to Store/Recall, Best Practices) with no nested references; slightly above 50 lines so it does not fully qualify for the simple-skill 5, sitting at 'good structure; minor organization gaps'.	4 / 5
	Total	16 / 20 Passed

Description

83%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 clearly states what the skill does and when to use it with natural trigger phrases, scoring well across all dimensions. Its main limitation is that the trigger terms and 'when' clause are somewhat generic rather than richly specific, leaving minor overlap risk with related memory skills.

Dimension	Reasoning	Score
Specificity	Lists several concrete capability areas (preferences, learnings, procedure outcomes) with concrete actions (store, remember, recall), matching the 'several specific actions; minor gaps' anchor rather than the comprehensive coverage of 5.	4 / 5
Completeness	Explicitly answers both what ('Store user preferences, learnings from tasks, and procedure outcomes') and when ('Use to remember what works and recall context before new tasks') with concrete trigger phrases, matching the exemplary anchor.	5 / 5
Trigger Term Quality	Includes natural phrases a user would say ('remember what works', 'recall context before new tasks') but lacks synonyms and common variations, sitting at 'good keyword coverage; a few natural terms missing' rather than the comprehensive anchor.	4 / 5
Distinctiveness Conflict Risk	Clear memory/persistence niche with distinct triggers, but 'remember what works' and 'recall context' carry minor overlap risk with general context/memory skills, fitting 'mostly distinct; minor overlap risk' over the minimal-conflict anchor of 5.	4 / 5
	Total	17 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: vectorize-io/hindsight
Path: skills/hindsight-local/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.