agentleFS
stevehansenstevehansen/eidet/.claude/skills/intake/SKILL.md

intake

Skill4 starsChanged 54 days agoMITView on GitHub

Prime on Eidet's intake pipeline before changing it — IntakeService's four verbs (whole-repo, docs-folder, git-history, Claude-Code-memory), the IIntakeExtractor/IIntakeSink contract, the per-candidate write gate, content-addressed dedup, the git commit gate and watermark. Use when the task touches an intake extractor, seeding memories from CLAUDE.md/README/manifests, git-history mining, Claude Code memory import, or a skip reason in an intake result. Not for pack import (see sharing), not for the /memories file store (see memorytool), not for turning seeds into insights (see maintenance).

34 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use triage, plan and 7 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • Google CloudSkill

    triage

    Gather context on a change or bug and plan the implementation.

    Also in 5 projects that use this

  • BlockSkill

    plan

    Draft a TDD, PRD, or lightweight plan in the conversation without committing it.

    Also in 4 projects that use this

  • Microsoft AzureSkill

    build

    Build the TypeSpec Rust emitter from source. Run this after cloning the repo, after pulling changes, or when TypeScript source files have been modified.

    Also in 3 projects that use this

  • AWSSkill

    retro

    Conduct a retrospective on a coding session.

    Also in 4 projects that use this

  • VercelSkill

    deploy

    Deploy applications to Vercel. Use when the user says "deploy", "deploy to Vercel", "push to production", "deploy my app", or "go live".

    Also in 3 projects that use this

  • Microsoft AzureSkill

    verify

    End-to-end app testing pipeline for browser-based web apps on cloud browsers via Azure Playwright Workspaces: verify the live app, author tests for working flows, heal failing tests, then re-run with video and produce one consolidated report. Three phases (app verification, test authoring, test healing) plus a scoped final sanity run; each phase emits a sub-report. Use when asked to "verify my app", "make sure my app works and has good test coverage", "do a full QA pass", "add tests where I'm missing coverage", "fix failing tests and add new ones", "smoke test before deploy", "QA my deployment", or any combined verify-and-test ask. Requires Azure CLI (`az login`) and a Playwright Workspace resource ID — bootstraps configs on first invocation. Browser-based web apps with Playwright only — not for unit/API tests, native mobile/desktop, load/perf, or full accessibility audits.

    Also in 4 projects that use this

The file

We split this skill into the rules it gives an agent

1 rule. 0 are common, 0 are distinctive, and 1 is very specific to this project.

  • 0

    Common

    Most of the 33 edited versions we read keep these.

  • 0

    Distinctive

    This author's own choices. Worth a look.

  • 1

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    No git repo ⇒ NullGitHistorySource ⇒ the run reports *skipped*, not failed.

    line 54

“Common” is measured: kept by at least 6 in 10 of the 33 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Intake — priming

Canonical spec: docs/domains/intake.md — read it for the four verbs, all invariants, key files, and gotchas. Terms of record: UBIQUITOUS_LANGUAGE.md § Lifecycle (Intake, Git-History Intake, Watermark).

IntakeService owns gating, dedup, store plumbing, dry-run, and result aggregation; each extractor knows exactly one source. Every seeded memory lands on the import trust floor (Provenance = Intake).

Core invariants (get these right)

  • The bulk write runs Validate: false on purpose — that path throws and aborts the batch. Intake calls WriteValidator.Validate per candidate in the sink: skip-not-abort, reason surfaced, and nothing is ever stored unscanned.
  • Blank a rejected candidate's content in the result — otherwise a caught secret leaks out through CLI/REST output.
  • Intake ids are content-addressed via MemoryIdGenerator — that's what makes re-ingest a single GetAsync probe, and minting locally would make every intake memory read as tampered.
  • Every skip carries a reason so "0 new" is never mysterious.
  • Git intake mines the pattern, never diff lines; the gate is a deterministic Conventional-Commits allowlist (fix → Procedure, feat/perf/refactor → Insight).
  • Read the git watermark before the run, advance it after (at-least-once; dedup absorbs replays). Dry runs never advance it.
  • Out-of-repo sources are opt-in and path-constrained — the Claude-memory extractor reads only the resolved per-project directory, and Eidet never writes there.
  • A verb runs only its own extractors (filtered by type), so file extractors never ride along on a git or interop run.
  • Markdown rules live only in MarkdownIntake — heading split, length floor, body-less predicate, tag mining.
  • A heading with no body is rejected, not stored (IsHeadingOnly, reason "heading with no body"). Length cannot catch it — ## Development Patterns is 23 chars — and every rendered form of a body-less memory has to be invented: 843 of 1,000 in the field carried a fabricated one-liner, 59 of which reached wake-ups. One letter or digit outside the headings/fences counts as a body.

Key files / reuse

  • src/Eidet.Core/Services/IntakeService.cs — the verbs and OrchestratorSink.
  • src/Eidet.Core/Intake/IIntakeExtractor.cs + IIntakeSink.cs — implement these to add a source.
  • src/Eidet.Core/Intake/MarkdownIntake.cs — reuse; don't re-split headings.
  • src/Eidet.Core/Intake/Git/IGitHistorySource.cs — the port (InMemoryGitHistorySource for tests).

Gotchas

  • Registered ≠ active: DocsFolder, ClaudeCodeMemory, and GitHistory extractors are inert until their IntakeOptions switch is set. An ungated new extractor fires on every whole-repo intake.
  • Dry run still gates and probes for duplicates; it just writes nothing.
  • Git mining is capped per commit (files, regions, hunks, body chars) — big commits truncate.
  • No git repo ⇒ NullGitHistorySource ⇒ the run reports skipped, not failed.

Download now (ZIP)

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
What did you use it for? e.g. Reviewing pull requests in a Rails app

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.