hindsight-self-hosted

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

Quality

66%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./skills/hindsight-self-hosted/SKILL.md

Quality

Content

65%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 skill is highly actionable with concrete executable commands and a scripted setup flow, and the product-specific pipeline explanation earns its place. It loses points for a redundant Best Practices section, absent validation/feedback loops on the core operations, and a long monolithic body that could offload detail to a reference.

Suggestions

Remove or collapse the 'Best Practices' section where it duplicates 'When to Store Memories'/'When to Recall Memories' to recover token budget.

Add a brief validation/feedback step after retain/recall (e.g. check the command's exit status or confirm recall returned relevant results before proceeding).

Move the detailed 'When to Store Memories' category lists and the transcript example into a one-level-deep reference file (e.g. references/when-to-store.md) and link to it from the body.

Dimension	Reasoning	Score
Conciseness	The body is mostly efficient and the 'How Hindsight Works' section is product-specific rather than generic Claude knowledge, but the 'Best Practices' list substantially restates the earlier 'When to Store'/'When to Recall' sections.	2 / 3
Actionability	It provides concrete, copy-paste-ready commands ('hindsight memory retain <bank-id> "..." --context procedures', recall, reflect) plus a fully scripted setup flow with curl/mkdir/cat/chmod examples.	3 / 3
Workflow Clarity	Setup is a clear 3-step sequence with a config check, but the core store/recall/reflect operations have no validation checkpoints or error-recovery feedback loops (e.g. confirming a retain succeeded or handling a recall failure).	2 / 3
Progressive Disclosure	The single SKILL.md is well-sectioned with clear headers and no nested references, but at ~150 lines the detailed 'When to Store' category lists and the transcript example are inline content that could be split into a one-level-deep reference file.	2 / 3
	Total	9 / 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 cleanly answers both what the skill does and when to use it with an explicit trigger clause, and stays in third-person voice. It is somewhat held back by general verb-based actions and memory language that overlaps other memory skills.

Suggestions

Sharpen specificity by naming concrete operations (e.g. 'Store, recall, and reflect on team memories via the hindsight CLI') rather than general verbs over categories.

Broaden trigger terms to include phrases users naturally say, such as 'what did we learn on this project', 'team conventions', or 'check past learnings before starting'.

Dimension	Reasoning	Score
Specificity	The description lists multiple actions ('Store team knowledge, project conventions, and learnings', 'remember what works', 'recall context before new tasks'), but these are general verbs applied to categories rather than the granular concrete operations of the top anchor.	2 / 3
Completeness	It explicitly answers 'what' ('Store team knowledge... Connects to a self-hosted Hindsight server') and 'when' with an explicit 'Use to remember what works and recall context before new tasks' trigger clause.	3 / 3
Trigger Term Quality	Natural phrases like 'team knowledge', 'recall context', and 'remember what works' appear, but coverage of common user variations (e.g. 'what did we learn', 'team conventions') is incomplete.	2 / 3
Distinctiveness Conflict Risk	The self-hosted Hindsight / shared-team-bank framing is a distinct niche, but the generic memory language ('remember', 'recall context') could overlap with other memory skills.	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-self-hosted/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.