Not in the top 1,000 by GitHub stars

EfficientStreet/hindsight

A self-improvement skill for AI coding assistants — reviews a session end-to-end and saves only the durable process lessons as persistent memory.

History

Review weekly changes to SKILL.md before updating. Dates mark the weeks in which we observed each version; checks apply to the recorded commits.

View weekly changes

SKILL.md

Week of Oct 26, 2026 · Line counts unavailable

Before Not checked yet → After Instructions only

First observation → d43d7282058b

No earlier version was observed for comparison.

Compare on GitHub

View on GitHubAdd to my skills

Verified commit d43d7282058b41d31110be47612623ab2cc3eeb5

173GitHub stars
-1star in 7 days
1skill in this repository
0commits in 30 days

Heat

0.1
  • Star growth, last 7 daysNot available
  • Star growth, last 24 hoursNot available
  • Rank movement, last 7 daysNot available
  • Commits, last 30 daysNot available
  • Accounts asking about it through MCP, last 7 daysNot available
  • Hot votes this weekNot available

Heat never changes the order by stars, and sponsorship never touches it. How heat works

Stars over time

Oct 25, 2026Nov 6, 2026174

30-day change not yet available: not enough history.

Individual skills in this repository

How it works

hindsight

When your agent uses it

Reviews everything accomplished in the current session end-to-end, distills genuine process lessons (not one-off content specifics), and saves the durable ones as persistent memory — updating an existing related memory in place rather than duplicating it. Trigger on "get some hindsight," "run a hindsight pass," "what should we improve," "review today and notate lessons," "what did you learn today," "save what's worth remembering from this session." Does not redo or re-open any of the session's actual work, and never fabricates a lesson just to have something to report.

What it loads into context

Frontmatter

142 tokens

Always available to the agent

SKILL.md

1,852 tokens

When the skill is activated

Reference documents

2,610 tokens

Loaded on request

Token counts are estimates. Scripts run separately; they are not counted as reference context.

The playbook

  1. When this fires
  2. Process
  3. In this environment
  4. Definition of done
  5. Scope boundary

Files

  • .gitignoreasset63 bytes
  • GUIDE.mddoc7,660 bytes
  • LICENSEasset1,075 bytes
  • README.mddoc4,107 bytes
  • SKILL.mdcore8,631 bytes
  • docs/hindsight-infographic.jpgasset2,693,693 bytes
Read SKILL.md

# Hindsight

A session-end self-improvement pass. Read-only against the session's actual
work — it never redoes or re-opens a task — and write-only against memory.
User-triggered only: a hindsight pass writes persistent memory, so timing
stays the user's call, never something run on a hunch.

## When this fires

On-demand only: "get some hindsight," "run a hindsight pass," "what should
we improve," "review today and notate lessons," "what did you learn today,"
"save what's worth remembering from this session."

## Process
View the complete source on GitHub

Skills included

  • hindsight

Repository facts

License
MIT
Created
Aug 20, 2026
Last pushed
Aug 20, 2026
Forks
28
Open issues
0
Project activity
Slowing

Before you install

Instructions only

Automated signals, not a guarantee

Checked Nov 6, 2026

  • No broad tool permissions
  • No dangerous shell commands
  • 8 network referencesin 2 files: GUIDE.md:160 README.md:97
  • No hidden or obfuscated text
  • No instruction overrides
  • No executable scripts
  • No access to secrets
  • No requests to vote in Hot
Show all 8 signals by file

GUIDE.md

  • Network accessline 160
    **Jeffrey Smith** Email: jeffrey@efficientstreet.com YouTube: https://youtube.com/@JeffreyEntrepreneur
  • Network accessline 161
    Email: jeffrey@efficientstreet.com YouTube: https://youtube.com/@JeffreyEntrepreneur Website: https://efficientstreet.com
  • Network accessline 162
    YouTube: https://youtube.com/@JeffreyEntrepreneur
  • Network accessline 163
    Website: https://efficientstreet.com

README.md

  • Network accessline 97
    **Jeffrey Smith** Email: jeffrey@efficientstreet.com YouTube: https://youtube.com/@JeffreyEntrepreneur
  • Network accessline 98
    Email: jeffrey@efficientstreet.com YouTube: https://youtube.com/@JeffreyEntrepreneur Website: https://efficientstreet.com
  • Network accessline 99
    YouTube: https://youtube.com/@JeffreyEntrepreneur
  • Network accessline 100
    Website: https://efficientstreet.com

How the signals fit together

Facts from a static read of the files at the pinned commit. They describe what the code does, not why.

Signal confidence: 8 facts
  • Network access in prose of documentationGUIDE.md:160Low confidence
  • Network access in prose of documentationGUIDE.md:161Low confidence
  • Network access in prose of documentationGUIDE.md:162Low confidence
  • Network access in prose of documentationGUIDE.md:163Low confidence
  • Network access in prose of documentationREADME.md:97Low confidence
  • Network access in prose of documentationREADME.md:98Low confidence
  • Network access in prose of documentationREADME.md:99Low confidence
  • Network access in prose of documentationREADME.md:100Low confidence

Works with

Agent compatibility, from the files in this repository
AgentStatusEvidenceInstall to
Claude CodeNativeFrontmatter field disable-model-invocation in SKILL.md.claude/skills/<skill-name>/
CodexCompatibleStandard SKILL.md SKILL.md.agents/skills/<skill-name>/
CursorCompatibleStandard SKILL.md SKILL.md.cursor/skills/<skill-name>/
Gemini CLICompatibleStandard SKILL.md SKILL.md.gemini/skills/<skill-name>/
GitHub CopilotCompatibleStandard SKILL.md SKILL.md.github/skills/<skill-name>/
OpenCodeCompatibleStandard SKILL.md SKILL.md.opencode/skills/<skill-name>/
  • Native The repository ships a manifest, folder or frontmatter field for this agent.
  • Compatible A standard SKILL.md that this agent can read.
  • Unknown No evidence either way.

Derived automatically from paths, manifests and frontmatter. Not tested on each agent.