learning-harvest
Skill18 starsChanged yesterdayMITView on GitHub
Distill proven recurring friction from substantive work into reusable rules, skills, or tests, or prune stale instructions. Not for one-off incidents, speculation, or restating code/git history.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- techygarg/latticetheir own version, first seen Oct 13, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- techygarg/lattice★ 209same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository13 other files it gives its agents.
- .changelog.d/CLAUDE.mdCLAUDE.md
- CLAUDE.mdCLAUDE.md
- ai-gateway-loop-optimizationSkill
- clean-codeSkill
- console-e2eSkill
- console-handoffSkill
- console-performanceSkill
- design-sweepSkill
- git-worktreeSkill
- product-proposalSkill
- pr-workflowSkill
- rebase-on-canarySkill
- release-version-updateSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 8
Keep non-obvious learning from completed work in one retrievable, actionable home.
- Distinctive: line 34
Check existing homes for duplicates first.
- Distinctive: line 42
Verify links, commands, and ownership.
- Distinctive: line 44
If nothing survives, say so briefly and finish.
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Learning Harvest
Keep non-obvious learning from completed work in one retrievable, actionable home. Do not let instructions accumulate faster than signal. This skill does not add product features.
Trigger and approval
On explicit request or after substantive work, briefly propose candidates. Do not claim an automatic hook ran. New persistent encodings and deletions require user approval of the candidates. Do not repeat approval for a specific update already authorized by the request.
Candidate gate
Review actual friction, discoveries, judgment calls, and skills used. A candidate must satisfy all three:
- Recurrence: will the situation happen again?
- Cost: was the obstacle costly or non-obvious enough?
- Generality: does the learning apply beyond that single incident?
Discard candidates that fail any condition. Incorrect commands or missing skill boundaries are candidates too, but one model mistake does not justify a universal model rule.
Route to one home
| Learning | Preferred owner |
| Reproducible regression/defect condition | Test or automated check |
| Repeatable procedure | Existing skill; new skill only if no suitable home exists |
| Procedure-specific trap | That skill's conditional reference/gotcha |
| Stable, expensive-to-violate rule needed before scoped work | Nearest CLAUDE.md |
| User preference or working feedback | Persistent memory |
Check existing homes for duplicates first. Propose migration rather than copying when a better home exists. CLAUDE.md additions must pass root risk-weighted minimalism; do not accumulate handbooks or inventories. Prefer enforceable tests/scripts over prose when feasible.
Propose, apply, verify
- Encode each survivor concisely as
symptom → action → why (failure mode). Include evidence for all three conditions, the owning home, and duplicates/migration. - Inspect the touched surface and propose keep/update/delete dispositions too. Pruning review is required; unnecessary deletion is not.
- Apply only approved items. Repository changes use a dedicated worktree; Memory follows its current write contract. For approved repository changes, follow the root
CLAUDE.mdstanding delivery authorization throughpr-workflow, honoring local-only requests and narrower scopes; this does not approve an unapproved candidate or replace memory approval. - Skill edits use narrow descriptions, conditionally loaded references, and explicit completion/stop conditions. Keep stable boundaries rather than adding model-performance claims or ceremonial investigation/testing steps.
- Verify links, commands, and ownership. Check that the rule resolves its target case without blocking neighboring normal cases. Do not persist unverified generalizations.
If nothing survives, say so briefly and finish. Stop at proposal when awaiting approval; after authorized encoding, report locations, changes/removals, and verification. Do not prolong the task with endless retrospection or new-skill creation just to manufacture learning.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

