Run any Skill in Manus with one click

engraim-onboard

Stars1

Forks0

UpdatedJuly 2, 2026 at 01:56

Set up a brand-new EngrAIm workspace for a folder/project. Use on first run (the SessionStart nudge), when the user runs /engraim:onboard, or when adopting EngrAIm into an existing project. Scans the project deterministically, seeds the memory frame (ENV/USER/SOUL), offers history backfill and optional semantic recall, and explains the workflow — without turning it into an interrogation.

Installation

Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.

Run Skill in Manus

Source

Redth

Redth/engrAIm

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Computer Occupations, All OtherComputer and Mathematical Occupations·SOC 15-1299

SKILL.md

readonly

name	engraim-onboard
description	Set up a brand-new EngrAIm workspace for a folder/project. Use on first run (the SessionStart nudge), when the user runs /engraim:onboard, or when adopting EngrAIm into an existing project. Scans the project deterministically, seeds the memory frame (ENV/USER/SOUL), offers history backfill and optional semantic recall, and explains the workflow — without turning it into an interrogation.

Onboard a workspace

Goal: get a new workspace from empty stubs to genuinely useful in a couple of minutes, mostly from what can be detected rather than what the user has to type.

Steps

Opt in. Call the enable tool first — it creates .engraim/ if missing (idempotent). EngrAIm is inert in a project until this runs, and the SessionStart hook no longer adopts projects automatically, so this is what actually turns memory on here.
Scan. Call scan_project (read-only). Summarize for the user what this project is: languages, build tooling, package scripts, git remotes, notable top-level files.
Seed the frame by editing files in .engraim/frame/ directly:
- ENV.md — the durable, bounded environment facts worth injecting every session (stack, tooling, key conventions detected). Keep it tight; it's a hot tier.
- SOUL.md — operating rules that are obvious from the project (e.g. "this is a library, keep the public API stable") — only what you're confident about.
- USER.md — ask one short question about working/communication preferences (or infer from how the user talks). Don't interrogate.
Offer backfill. Suggest /engraim:backfill to bootstrap memory from past Claude Code sessions in this project (note older transcripts may already be trimmed). 3b. Offer a .gitignore suggestion (don't write without asking): recommend the project ignore .engraim/store.db (rebuildable index) and .engraim/vendor/ (optional deps), and commit the rest of .engraim/ (wiki + frame are canonical, diffable knowledge).
Mention semantic recall as optional: /engraim:enable-semantic. Make clear keyword recall already works and semantic is a nice-to-have that adds a dependency.
Finish. Call mark_onboarded (stops the first-run nudge) and give a two-line tour: just work normally — sessions are captured and distilled (/engraim:curate), corrections become calibration (/engraim:calibrate), recurring procedures can become skills (/engraim:draft-skill), and /engraim:lint surfaces knowledge gaps.

Discipline

Prefer detected facts over asked ones. Every question has a cost.
Seed, don't overfit: a few solid frame lines beat a wall of speculation.
Don't record secrets from config files you scan.

More from this repository

same repository

engraim-calibrate

Redth/engrAIm

Record and manage how Claude should BEHAVE in this workspace — corrections, conventions, do/don't rules, tone. Use WHENEVER the user corrects you, states a preference, expresses frustration with an approach, or a `verdict:` annotation comes back negative. Also use to reaffirm, promote, or retire existing behavior overrides. This is the workspace's self-improving frame; it's distinct from facts about the world (use engraim-memory for those).

2026-06-301

engraim-curate

Redth/engrAIm

Distill session transcripts into durable memory. Use when processing staged sessions (after the Stop hook), when the user runs /engraim:curate or /engraim:backfill, or whenever you should turn "what just happened" into lasting knowledge. Turns raw Claude Code session JSONL into wiki pages + temporal facts, with provenance and no secrets.

2026-06-291

engraim-memory

Redth/engrAIm

How to use the workspace's persistent memory. ALWAYS use this whenever you need to recall what was learned about THIS project/environment before, or whenever you learn something durable worth keeping. Use it for: "what do we know about X", recalling prior decisions, conventions, environment quirks, fixes, inventory; and for recording new durable facts. Drives the `engraim-memory` MCP tools (recall, remember, whats_true, wiki_get, wiki_upsert). Prefer recalling from memory before searching the web or asking the user to re-explain context.

2026-06-291

engraim-research

Redth/engrAIm

The research-as-intake reflex. Use this WHENEVER you hit a knowledge gap or an error you can't resolve from memory — instead of guessing or giving up, search the web, prefer canonical sources, solve the problem, and intake the verified finding into the workspace knowledge base. Trigger on: unfamiliar errors, "how do I do X", version-specific behavior, tool/config questions about this environment, or anything where memory came up empty.

2026-06-291

engraim-retro

Redth/engrAIm

Run a periodic, GUARDED retrospective over the workspace memory: consolidate learnings, resolve verdicts, prune stale overrides, surface promotions. Use when the user runs /engraim:retro, when status shows many pending sessions or expiring overrides, or when a body of work has accumulated and the memory needs tightening. Enforces an echo-chamber guardrail and an action test so the retrospective improves the memory rather than just reinforcing it.

2026-06-291

engraim-skillsmith

Redth/engrAIm

Author, review, and promote workspace-local skills so this project can grow its own capabilities. Use when a multi-step procedure recurs across sessions, when the user says "make this a skill" / "automate this", or when running /engraim:draft-skill, /engraim:promote-skill, or /engraim:skills. Drives the draft -> gate -> activate pipeline (draft_skill, review_skill, promote_skill, list_skills, retire_skill). Composes with Anthropic's skill-creator when it's available rather than duplicating it.

2026-06-291

name	engraim-onboard
description	Set up a brand-new EngrAIm workspace for a folder/project. Use on first run (the SessionStart nudge), when the user runs /engraim:onboard, or when adopting EngrAIm into an existing project. Scans the project deterministically, seeds the memory frame (ENV/USER/SOUL), offers history backfill and optional semantic recall, and explains the workflow — without turning it into an interrogation.

Onboard a workspace

Goal: get a new workspace from empty stubs to genuinely useful in a couple of minutes, mostly from what can be detected rather than what the user has to type.

Steps

Opt in. Call the enable tool first — it creates .engraim/ if missing (idempotent). EngrAIm is inert in a project until this runs, and the SessionStart hook no longer adopts projects automatically, so this is what actually turns memory on here.
Scan. Call scan_project (read-only). Summarize for the user what this project is: languages, build tooling, package scripts, git remotes, notable top-level files.
Seed the frame by editing files in .engraim/frame/ directly:
- ENV.md — the durable, bounded environment facts worth injecting every session (stack, tooling, key conventions detected). Keep it tight; it's a hot tier.
- SOUL.md — operating rules that are obvious from the project (e.g. "this is a library, keep the public API stable") — only what you're confident about.
- USER.md — ask one short question about working/communication preferences (or infer from how the user talks). Don't interrogate.
Offer backfill. Suggest /engraim:backfill to bootstrap memory from past Claude Code sessions in this project (note older transcripts may already be trimmed). 3b. Offer a .gitignore suggestion (don't write without asking): recommend the project ignore .engraim/store.db (rebuildable index) and .engraim/vendor/ (optional deps), and commit the rest of .engraim/ (wiki + frame are canonical, diffable knowledge).
Mention semantic recall as optional: /engraim:enable-semantic. Make clear keyword recall already works and semantic is a nice-to-have that adds a dependency.
Finish. Call mark_onboarded (stops the first-run nudge) and give a two-line tour: just work normally — sessions are captured and distilled (/engraim:curate), corrections become calibration (/engraim:calibrate), recurring procedures can become skills (/engraim:draft-skill), and /engraim:lint surfaces knowledge gaps.

Discipline

Prefer detected facts over asked ones. Every question has a cost.
Seed, don't overfit: a few solid frame lines beat a wall of speculation.
Don't record secrets from config files you scan.