agentleFS
Sign inStart free
askoulwassimaskoulwassim/perfect-placement/skills/learn/SKILL.md

learn

Skill3 starsChanged 33 days agoMITView on GitHub

Turn learning events (picks, skips, closed roles, rejections, interview retros, outreach replies, offers, overridden decisions) into profile diffs with evidence. The policy decides what applies; filters and dealbreakers always wait for the user.

195 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use add-anydoc, add-clidash and 10 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.
  • TomGranotSkill

    add-anydoc

    Add local office-document-to-Markdown conversion to NanoClaw agent containers with the pinned Firecrawl AnyDoc CLI. Use when agents need to read attached Word, PowerPoint, Excel, OpenDocument, RTF, EPUB, CSV, or text-based PDF files without uploading them to a hosted parser.

    Also in 5 projects that use this

  • TomGranotSkill

    add-clidash

    Add clidash — a zero-dependency, read-only web dashboard that derives its tabs and tables at runtime from any CLI that lists resources as JSON. Ships pre-wired for NanoClaw's ncl CLI (agent groups, sessions, channels, users, roles), plus message-activity charts, a log tail, and a read-only file viewer for group skills/CLAUDE.md/profiles.

    Also in 5 projects that use this

  • seek888Skill

    open-gstack-browser

    Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome", "open chrome", "real browser", "launch chrome", "side panel", or "control my browser". Voice triggers (speech-to-text aliases): "show me the browser".

    Also in 11 projects that use this

  • Saqlain-811Skill

    ios-sync

    Regenerate the iOS debug bridge against the latest upstream gstack templates. (gstack)

    Also in 6 projects that use this

  • MicrosoftSkill

    add-codex

    Use Codex (CLI + AppServer) as the full agent provider — planning, tool orchestration, native compaction, MCP tools, session resume — in place of the Claude Agent SDK. ChatGPT subscription or OPENAI_API_KEY. Per-group via agent_provider. Distinct from using OpenAI as an MCP tool (where Claude remains the planner).

    Also in 6 projects that use this

  • MicrosoftSkill

    add-deltachat

    Add DeltaChat channel integration via @deltachat/stdio-rpc-server. Native adapter — no Chat SDK bridge. Email-based messaging with end-to-end encryption.

    Also in 6 projects that use this

  • +5 more from TomGranot
  • +1 more from microsoft

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 170 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:

    Keep the component's schema: the same keys and value types profile.get returns (the op validates it.

    line 26

“Common” is measured: kept by at least 6 in 10 of the 170 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

learn

Supplies judgment only; every write is an op. Never submit an application or send an email.

Trigger

Any event in LEARNING_EVENTS: role_picked, role_skipped, role_closed, rejection, interview_retro, outreach_replied, offer, decision_overridden. The engine runs the loop (learnFromEvent, exposed as an op in Wave 2); this skill is the judgment the loop asks for when an LLM backend is an agent.

Judgment you supply

  1. Does this event change a component? For each of the 11 components the resolver asks a yes/no. Answer from the event and the component's current data only. One rejection rarely proves a preference; say no unless the event is direct evidence (explicit feedback, an offer's terms, a pattern across several events).
  2. Draft the diff for each yes: { before, after, evidence }.
    • after holds only the top-level keys you change; before the same keys' current values (the engine recomputes before from the data anyway).
    • evidence: short factual lines pointing at the event(s): role id, stage, quoted feedback. No speculation.
    • Return nothing when on reflection nothing should change.
    • Keep the component's schema: the same keys and value types profile.get returns (the op validates it; the schema is packages/engine/profile/components.ts in the repo, never in the vault). Never change criterion_weights by more than 3 points per criterion from one event.
  3. Then call profile.propose_diff { component, before, after, evidence, event_id }, and profile.apply_diff { diff_id } with your confidence: routing is policy, never your call.

Policy (mechanics, for reference)

Component kindImpactOutcome (#14, #24)
Dealbreakers; Terms when the comp floor changeshard exclusionalways the user, in Needs you
Work mode, other Terms changes (filters)highauto + 24h undo when p >= 0.90, else the user
Craft, Domain, Company, Team, Growth (weighted)mediumauto + 24h undo when p >= 0.90; 0.70 to 0.90 only if a second opinion agrees; else the user
Story, Voice, Network (assets)mediumsame as weighted

profile.learn { event_id } runs the loop: it asks the 11 yes/no questions through the resolver. When the engine has no writing model (the default), you draft each diff and call profile.propose_diff; then call profile.apply_diff with your confidence in the op context, and the policy decides. Applied weighted and filter changes create profile v+1 and rescore the movable roles (inbox, active, held; never a role the user picked).

Tools

A headless run pre-approves exactly these (SKILL_GRANTS in packages/engine/runners/grants.ts; a test keeps this list and that one equal) and denies everything else. If one you need is denied or missing, do not work around it: runs.finish { run_id, status: "error", summary: { error: "tool denied: <tool>", denied_tools: [...] } }.

  • {{tool:pp}}: the pp MCP tools (every Perfect Placement read and write is an op).

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.

Check your setup, free