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

78%

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

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-structured, highly actionable skill body with copy-paste commands, a sequenced setup workflow, and clear storage/recall guidance. It loses points only on minor redundancy in Best Practices and the absence of error-recovery feedback loops and external reference splitting.

Suggestions

Add an error-recovery branch to the setup workflow (e.g., what to do if the curl install fails or credentials are rejected).

Trim the Best Practices section to remove items that restate earlier sections, or fold the long transcript example into a reference file to improve token efficiency.

Consider moving the detailed 'When to Store' category lists into a references/ file linked from the main body to better leverage progressive disclosure.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient with concrete commands and product-specific guidance (e.g., the Hindsight pipeline explaining why to pass rich context), but the Best Practices section restates earlier points ("Pass rich context", "Distinguish project vs personal") and the multi-line transcript example is token-heavy — minor trim opportunities keep it at 4 rather than 5.	4 / 5
Actionability	Commands are fully executable and copy-paste ready — `hindsight memory retain\|recall\|reflect <bank-id>` with real example strings, the `--context` flag, plus complete setup commands (curl install, config file creation with chmod) — covering the common cases, matching the score-5 anchor.	5 / 5
Workflow Clarity	The Setup Check is a clear sequence with a verification checkpoint ("verify the Hindsight CLI is configured" via `cat ~/.hindsight/config`, branching if missing), and "When to Recall" provides a checklist; not a 5 because there is no error-recovery feedback loop (e.g., what to do if the install or credentials fail).	4 / 5
Progressive Disclosure	Content is well-organized into clearly headed sections (Setup, How Hindsight Works, Commands, When to Store/Recall, Best Practices) with easy navigation and no bundle files to misreference; not a 5 because at ~150 lines with no external references, some inline material (the long transcript example, detailed category lists) could be split into reference files, and the under-50-line simple-skill exception does not apply.	4 / 5
	Total	17 / 20 Passed

Description

75%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 solid description that clearly states what the skill does and when to use it, with concrete actions and a distinct Hindsight Cloud niche. It falls short of top marks only in lacking concrete user-utterance trigger phrases and a few natural synonyms.

Suggestions

Add a 'Use when the user mentions team knowledge, project conventions, past learnings, or asks to remember/recall context' style trigger clause with concrete user-utterance phrases.

Include natural synonyms like 'memory' or 'notes' alongside 'team knowledge' to broaden trigger coverage.

Drop the trailing '(user)' annotation, which adds no descriptive value.

Dimension	Reasoning	Score
Specificity	Lists several concrete actions — "Store team knowledge, project conventions, and learnings from tasks", "remember what works", "recall context before new tasks", "Connects to Hindsight Cloud" — matching the score-4 anchor of several specific actions with minor coverage gaps; not a 5 because "remember" and "recall" overlap and "Connects to Hindsight Cloud" is an integration note rather than a capability.	4 / 5
Completeness	Both "what" (store team knowledge/conventions/learnings; connects to Hindsight Cloud) and "when" ("Use to remember what works and recall context before new tasks") are present, with the "Use to...before new tasks" clause counting as equivalent explicit trigger guidance so the score-3 cap does not apply; not a 5 because the "when" states purpose rather than concrete user-utterance trigger phrases.	4 / 5
Trigger Term Quality	Natural phrases users would say are present ("team knowledge", "project conventions", "learnings", "remember what works", "recall context"), giving good keyword coverage; not a 5 because common synonyms like "memory", "notes", or "save this" are missing.	4 / 5
Distinctiveness Conflict Risk	The "shared team knowledge" framing plus the named "Hindsight Cloud" backend gives it a mostly-distinct niche with only minor overlap risk against other memory/context skills; not a 5 because "store knowledge / recall context" is a somewhat crowded category that could still overlap with generic note-taking skills.	4 / 5
	Total	16 / 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-cloud/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.