hindsight-cloud

Store team knowledge, project conventions, and learnings from tasks. Use to remember what works and recall context before new tasks. Connects to Hindsight Cloud. (user)

Quality

76%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Critical

Do not install without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/hindsight-cloud/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 highly actionable with executable commands and clear sequenced workflows including a setup validation checkpoint, and it is well-organized for a single-file skill with no external references. Its main weakness is mild redundancy between the Best Practices list and earlier sections.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and product-specific (the 'How Hindsight Works' pipeline detail is justified, not general knowledge), but the 'Best Practices' list restates points already covered in 'How Hindsight Works' and 'When to Store Memories', so it could be tightened to earn every token.	2 / 3
Actionability	It provides fully executable bash commands (retain/recall/reflect with real example payloads and a copy-paste setup block including config-file creation), matching the score-3 'fully executable; copy-paste ready' anchor.	3 / 3
Workflow Clarity	Setup is a clear validate-then-fix sequence ('cat ~/.hindsight/config' check, then install/configure/get-bank-id steps) and the recall-before-task / store-when-discovered flow is clearly sequenced, matching the score-3 anchor with explicit checkpoints.	3 / 3
Progressive Disclosure	No bundle files exist, so the single-file skill is appropriately organized into clear, navigable sections (Setup, How it Works, Commands, When to Store, When to Recall, Best Practices) with no nested references, matching the score-3 'well-organized sections' guidance for skills needing no external references.	3 / 3
	Total	11 / 12 Passed

Description

67%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 states both what it does and when to use it with an explicit trigger clause, but its action vocabulary and trigger terms are somewhat generic and abstract rather than sharply distinctive. It names a specific cloud integration but otherwise overlaps conceptually with general memory skills.

Suggestions

Replace abstract verbs with concrete enumerated actions (e.g., 'Store coding standards, bug fixes, and onboarding notes; recall them before starting a task') to lift specificity toward score 3.

Add distinctive natural trigger terms users would actually say (e.g., 'Use when onboarding to a codebase, before refactoring, or when a teammate asks how something works') to improve trigger-term quality and distinctiveness.

Tighten the integration claim so it distinguishes the skill from generic memory tools (e.g., name the shared team-bank behavior as the differentiator).

Dimension	Reasoning	Score
Specificity	The description names the domain ('team knowledge, project conventions, and learnings from tasks') and concrete verbs ('Store', 'recall context'), but the actions are somewhat abstract rather than multiple specific concrete actions like the score-3 anchor ('Extract text and tables... fill forms, merge documents').	2 / 3
Completeness	It explicitly answers both what ('Store team knowledge, project conventions, and learnings from tasks') and when via an explicit 'Use to remember what works and recall context before new tasks' trigger clause, matching the score-3 anchor.	3 / 3
Trigger Term Quality	It includes some relevant natural phrases ('remember what works', 'recall context before new tasks', 'project conventions'), but these are fairly generic and lack a distinctive technical trigger; coverage of natural user vocabulary is incomplete like the score-2 anchor ('Works with PDF files').	2 / 3
Distinctiveness Conflict Risk	'team knowledge, project conventions, and learnings' is a fairly generic memory niche that could overlap with other memory/context skills, though 'Connects to Hindsight Cloud' adds some specificity — matching the score-2 'somewhat specific but could still overlap' anchor.	2 / 3
	Total	9 / 12 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-cloud/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.