fde
Engagement fieldbook for Forward Deployed Engineers. Use when the human says @fde or asks about client memory, debrief, prep, receipts, trust, hygiene, or sponsor status — route and run the local fde CLI; never ask them to type fde commands. Do not use for ordinary code edits, unit tests, refactors, or git commits.
Profile →npx skills add suboss87/FDEOps --skill fde --agent claude-code
Same command for any agent — swap --agent for codex, cursor, copilot.
Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.
What it does
Routes to the local fde CLI for deterministic memory work when the human uses @fde or asks about client memory, debrief, prep, receipts, trust, hygiene, or sponsor status. It reads engagement context via the fde resume pathway, performs work to produce artifacts in the .fde/ folder, and writes memory updates as deliverables. It never asks the FDE to type fde commands and ensures outputs are written as artifacts (e.g., context.md, decisions.md, delivery.md) with explicit sources for each claim. It guides the human through artifact generation and memory writing as part of the engagement lifecycle.
How it works
- On entry, resolve the engagement path and read
context.mdviafde resume(bounded view: current state + recent activity). Pull other.fde/files only when the phase calls for them. - Deliverable = memory. The output of every phase is a
.fde/file written as the artifact. - Every claim in artifacts carries a source tag (e.g.,
(validated with: ops lead, Day 5)). Useunknown - ask: <question>for missing facts. - Do not invent facts; only include information provided by the FDE or repo.
- Use the local
fdeCLI for deterministic work and present results in plain language for confirmation, avoiding asking the FDE to run CLI commands. - Follow the engagement path rules (one engagement per
.fde/, never rewrite memory sections by removing required fields, and surface only the necessary references when routing). - Common actions include:
fde resume,fde debrief --apply,fde ingest propose,fde redact, andfde dashboarddepending on the task. Commands must be run verbatim by the agent; commands should not be handed to the FDE.
When to use it
Use when the human says @fde or asks about client memory, debrief, prep, receipts, trust, hygiene, or sponsor status. The skill routes to the appropriate fde phase and executes the work, updating memory accordingly. If setup is missing, run fde resume --init <name> after one clarifying question.
What it can touch
- The local fde CLI workspace and the
.fde/directory. It readscontext.mdand writes artifacts such ascontext.md,decisions.md, anddelivery.mdwithin the engagement folder as dictated by the phase.
Caveats
- The memory contract requires that output is memory (artifact) writing; avoid generating transcripts. Use sources for each claim. Do not ask the FDE to run
fdecommands themselves unless required by setup rules. The CLI is local only (no network) and data access is limited to the engaged.fde/files.
# @fde ## Audience (read this first) - **FDE** = the **human** who types `@fde` (or plain language) in the chat. - **You (the model)** = the **AI coding agent** running this skill - not a human colleague, not the client's staff. When this skill says "ask the FDE," it means the human. When it says "write to `.fde/`," you (the AI) write the files. ## Human surface vs agent plumbing (non-negotiable) | Who | Interface | |-----|-----------| | **FDE (human)** | `@fde` + natural language. Examples: "debrief these notes", "prep me for tomorrow's sponsor meeting", "when did we agree to drop that?", "draft the sponsor update". | | **You (agent)** | Run the local `fde` CLI for deterministic memory work. Never tell the FDE to type `fde …` (except if setup is missing - then **you** run `fde resume --init <name>` after one clarifying question). | If you catch yourself saying "run `fde debrief --smart notes.txt`" to the human - **stop**. Run it yourself (or write a temp notes file and run it), then show the human the result in plain language for confirm/reject. ## Purpose The single entry point for an entire client engagement. Field methods cover the FDE lifecycle (land through close, plus daily
- Audience (read this first)
- Human surface vs agent plumbing (non-negotiable)
- Purpose
- The memory contract (non-negotiable)
- Anti-invention gates (field anti-slop)
- Data boundary (confirm before touching their code)
- Proactive intelligence (run on every session start)
- Conversational voice
- The checkpoint question - ask before you cross a line
- Two-way co-pilot (not one-way recording)
- Forward momentum (after writing memory)
- Routing - 6 domains
- Domain 1 - Embed & Trust
- Domain 2 - Discover & Diagnose
What does the fde skill do?
Engagement fieldbook for Forward Deployed Engineers. Use when the human says @fde or asks about client memory, debrief, prep, receipts, trust, hygiene, or sponsor status — route and run the local fde CLI; never ask them to type fde commands. Do not use for ordinary code edits, unit tests, refactors, or git commits.
How do I install it?
Run `npx skills add suboss87/FDEOps --skill fde --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.
Where does this skill come from?
From suboss87/FDEOps, a repository with 247 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.
Is a popular skill a good skill?
Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.