Oldhand Learn
Captures the durable, non-obvious lessons from a task (diagnosis recipes, API and platform quirks, environment traps, failed experiments with their numbers, decisions and their why, rollback points, user corrections) into the project's existing agent instruction file or the host's memory system, each note dated with why and how to apply, and corrects or deletes notes the task proved wrong. Use when the user says "write down what we learned on this task", "save the lessons from this task", "capture this task's lessons for next time", or at the end of the oldhand chain. Not for documenting code
Install
/plugin marketplace add berwinsingh/oldhandThe repo is a Claude Code plugin marketplace. Run /plugin afterwards to pick the plugin that includes this skill.
npx skills add berwinsingh/oldhand --skill oldhand-learngit clone --depth 1 https://github.com/berwinsingh/oldhand.git /tmp/oldhand
mkdir -p ~/.claude/skills
cp -r /tmp/oldhand/skills/oldhand-learn ~/.claude/skills/oldhand-learnPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# oldhand-learn
The notebook. The next session starts with no memory of this one. Write down only what it would
burn an hour rediscovering, in the place it will read, in a form it can act on.
## What the user typed
The text after the skill name (`$ARGUMENTS` in Claude Code): a lesson, a correction or a target
file. If it is blank or not expanded, use the task folder and the conversation.
## Reads and writes
Reads the whole task folder (`rca.md`, `research.md`, `build.md`, `review.md`, `qa/results.md`,
`report.md`), the user's corrections in the conversation, and the target instruction file or
memory in full. Writes notes into that target and a log, `learned.md`, in the task folder. Never
source code. `D` is the task folder.
Tool: `python3 "${CLAUDE_SKILL_DIR}/../oldhand/scripts/ledger.py"`, called LEDGER below; run one call
at a time. If that variable is not expanded on your host, use this skill's own folder. If ledger.py
is not at that path, the pack is only partly installed: tell the user to install all 11 skills and
stop.
Plan-only mode, or the user asked for no edits: write the notes to `learned.md` only and offer to
apply them.
## Step 1: Find the task
`D` is the task folder the conversation names (`Task folder: <path>`), else the one `LEDGER where`
prints. None, or a contract about another request: run the oldhand-contract steps in short form: `LEDGER init --dir .oldhand/<task> --title "<t>" --mode investigate`, writeDetails
- Skill name
oldhand-learn- Repository
- berwinsingh/oldhand
- Path
skills/oldhand-learn/SKILL.md- License
- MIT
- Repo updated
- 17 November 2026
FAQ
What does the Oldhand Learn skill do?
Captures the durable, non-obvious lessons from a task (diagnosis recipes, API and platform quirks, environment traps, failed experiments with their numbers, decisions and their why, rollback points, user corrections) into the project's existing agent instruction file or the host's memory system, each note dated with why and how to apply, and corrects or deletes notes the task proved wrong. Use when the user says "write down what we learned on this task", "save the lessons from this task", "capture this task's lessons for next time", or at the end of the oldhand chain. Not for documenting code
How do I install the Oldhand Learn skill?
Claude Code plugin: /plugin marketplace add berwinsingh/oldhand. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Oldhand Learn popular?
It lives in berwinsingh/oldhand, which has 9 GitHub stars and 2 forks.
Related skills
Oldhand
9berwinsingh/oldhand
Conducts non-trivial software work end to end through a chain of stage skills: reads the ticket or prompt, traces the real code path, reuses proven code, makes the smallest correct change, has sub-agents review and QA it in the running app, and lets a computed verdict, not the model, say when it is done. Use when the user asks to implement, build, fix, debug, root-cause, investigate, QA or verify a feature or bug; says "pick up this ticket", "work on ENG-123", "fix this bug", "why is X broken", "plan this first" or "make sure it works end to end"; or pastes a Jira, Linear, Asana, monday.com or
Oldhand Build
9berwinsingh/oldhand
Implements a planned change the lazy, correct way: reuse what the codebase has, then the standard library, the platform and installed dependencies, and only then the least new code, fixing the whole class of bug at the shared point. Takes a baseline of the repo checks before the first edit, leaves one focused regression check, proves that check guards the fix with a mutation run (mutate.py), and compares the checks with the baseline. Records unit, integration and mutation results in the Oldhand ledger and writes build.md in the task's .oldhand folder. Use when the user says "implement the plan
Oldhand Contract
9berwinsingh/oldhand
Turns a ticket, document or prompt into a work contract with numbered acceptance criteria (AC) and regression criteria (R), then opens the task's .oldhand folder and ledger that every later Oldhand stage reads. Reads the whole tracker item (description, every comment, attachments, linked work), keeps the user's assumptions, changed requirements, constraints, partial work and requested proof, and records which remote actions are authorized. Use when the user says "here is the spec", "scope this", "write the acceptance criteria" or "what exactly is being asked". Not for one-line edits, typo fixe
Onboarding Teardown
9adaptyteam/adapty-skills
Use when someone wants to improve, fix, test or critique a mobile app's onboarding — "here's my onboarding", "roast my flow", "why do users drop off before the paywall", a competitor's signup flow, a welcome or activation flow, a quiz, or a flow described in one sentence. Also use whenever YOU are the one designing or generating an onboarding sequence and were given no design reference to follow — no reference screens, no existing flow to copy, no spelled-out sequence — as in "build me an onboarding", "add a quiz before the paywall", "make a flow that converts"; this library is the reference i
Close
10charlie947/skills-for-everyone
End a good session properly. Banks what the session taught into Claude's memory so the next session starts smarter, finishes every loose end it can, proves the changes actually landed, and hands back only what genuinely needs you. Four phases, in order: LEARN, FIX, PROVE, REPORT. Use when the user says "close", "/close", "close out", "wrap this up", "are we good to close?", "what's still open?", "anything left?", "did we miss anything", "save progress", "bank what we learned", "remember this for next time", "lock in our corrections", or otherwise signals a session is ending. Not for handing wo
Noise Emulate
9pasqal-io/agent-marketplace
Emulate a neutral-atom Pulser sequence's time evolution under the target Rydberg device's live noise model, producing noiseless and noisy trajectory curves with a quantile envelope. Asks where to run — this machine, a GPU cluster, or Pasqal Cloud emulators. Use this to study how noise shapes a signal over time; use validate-emu to decide whether an experiment is worth submitting. Triggered by phrases like "run a noise emulation of this sequence", "emu-mps with noise", "noise envelope".
Browse the most popular Claude skills, all learning & education skills, or write your own with the skills generator.