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

72%

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

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 CLI commands and a clear setup+usage workflow, well-organized into sections. Its main weakness is redundancy — several Best Practices points and one list item repeat earlier content — which inflates length without adding guidance.

Suggestions

Remove the duplicated 'Architecture decisions and their rationale' (appears in both Learnings from Tasks and Team Knowledge) and consolidate overlapping Best Practices points with the When to Store/Recall sections.

Add a brief error-recovery note for setup (e.g. what to check if 'hindsight memory retain' returns an auth error) to give the workflow a feedback loop.

Tighten the 'How Hindsight Works' section to the single actionable implication ('pass rich, full-context content; do not pre-summarize') rather than enumerating all four pipeline stages.

Dimension	Reasoning	Score
Conciseness	It is mostly efficient and free of generic-concept padding, but 'Architecture decisions and their rationale' is duplicated across Learnings and Team Knowledge, and the Best Practices section repeats guidance already covered in How Hindsight Works, When to Store, and When to Recall, so it could be tightened below 4.	3 / 5
Actionability	Commands are fully executable and copy-paste ready — 'hindsight memory retain <bank-id> "..."' with real --context flags, a transcript example, plus a complete setup heredoc — covering the common cases; the <bank-id> placeholder is explicitly explained.	5 / 5
Workflow Clarity	Setup has an explicit checkpoint (cat ~/.hindsight/config, branch to install if missing) and the recall-before-task / store-on-discovery sequence is clear; it stops at 4 because there is no error-recovery feedback loop (e.g. what to do if a retain fails or credentials are rejected).	4 / 5
Progressive Disclosure	No bundle files exist, so the skill is a single well-sectioned document with clear headers (Setup, How Hindsight Works, Commands, When to Store/Recall, Best Practices); the inline redundancy between Best Practices and earlier sections is a minor organization gap that keeps it from 5.	4 / 5
	Total	16 / 20 Passed

Description

70%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 gives an explicit use trigger, with a distinct self-hosted-Hindsight niche. It is slightly under-comprehensive on specific actions and trigger synonyms, landing solidly above average but not exemplary.

Suggestions

Add a 'Use when...' clause with concrete trigger phrases users would say, e.g. 'Use when starting a new task, recalling past decisions, or onboarding to a codebase'.

List a few more concrete actions (e.g. 'reflect on', 'attribute preferences to teammates') to raise specificity.

Include common synonym triggers like 'remember this', 'what did we decide', or 'team learnings'.

Dimension	Reasoning	Score
Specificity	Names the domain ('team knowledge, project conventions, and learnings from tasks') and two concrete actions ('Store', 'recall'), matching the 1-2 concrete actions anchor; it does not list several specific actions, so it stays at 3 rather than 4.	3 / 5
Completeness	It has a clear 'what' ('Store team knowledge, project conventions, and learnings from tasks') and an explicit 'when' ('Use to remember what works and recall context before new tasks'), but the 'when' lacks the concrete, varied trigger phrases of the 5-anchor, so it is 4 not 5.	4 / 5
Trigger Term Quality	Natural terms like 'team knowledge', 'project conventions', 'learnings', 'remember what works', and 'recall context' give good keyword coverage; it falls short of 5 because common synonyms and variations are absent.	4 / 5
Distinctiveness Conflict Risk	'Connects to a self-hosted Hindsight server' carves out a clear niche and the team-knowledge triggers are fairly specific; minor overlap risk with other memory skills keeps it just below 5.	4 / 5
	Total	15 / 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-self-hosted/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.