context-efficient
Skill1 starsChanged 41 days agoMITView on GitHub
Minimize token use while remaining correct. Use when working in large repos, long sessions, or when context pressure is high.
In this repository49 other files it gives its agents.
- accessibilitySkill
- address-feedbackSkill
- agent-disciplineSkill
- agent-handoffSkill
- api-designSkill
- architecture-decisionSkill
- brainstormSkill
- browser-verifySkill
- code-reviewSkill
- containerizeSkill
- create-prSkill
- database-changesSkill
- debug-systematicSkill
- dependency-upgradeSkill
- docs-groundedSkill
- error-handlingSkill
- explore-codebaseSkill
- fix-ciSkill
- frontend-designSkill
- git-commitSkill
- git-worktreeSkill
- incident-triageSkill
- incremental-slicesSkill
- legacy-changeSkill
- migrate-codeSkill
- minimal-diffSkill
- observabilitySkill
- parallel-workSkill
- performance-auditSkill
- plan-before-codeSkill
- python-qualitySkill
- react-componentsSkill
- refactor-safeSkill
- release-notesSkill
- security-reviewSkill
- setup-ciSkill
- shell-safetySkill
- ship-checklistSkill
- simplify-codeSkill
- skill-authoringSkill
- skill-routerSkill
- spec-drivenSkill
- tddSkill
- threat-modelSkill
- triage-issuesSkill
- typescript-strictSkill
- verify-workSkill
- write-docsSkill
- write-testsSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 3 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
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 10
Read the smallest useful slice of a file (offset/limit) before whole files.
- Distinctive: line 11
Prefer search hits with context over dumping directories.
- Distinctive: line 26
Run the narrowest query that resolves it.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
Context Efficient
Principles
- Read the smallest useful slice of a file (offset/limit) before whole files.
- Prefer search hits with context over dumping directories.
- Summarize large tool outputs; keep only facts needed for the next step.
- Reuse prior findings; do not re-read files already understood.
- One clear goal per tool batch; parallelize independent lookups.
Avoid
- Reading generated, lock, or minified files unless required.
- Pasting large logs into replies.
- Restating the full task in every step.
- Loading multiple skills that overlap; pick one primary workflow.
When Stuck
- State the unknown in one line.
- Run the narrowest query that resolves it.
- Continue; do not broad-scan “just in case.”
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.