Skip to content
Skills Library
Management & product · Learning & explanation

practice-model

/practice-model

Use when the question is which practice or project work belongs to: writing to another practice with --project-id, reading another practice's artifacts, working on a remote or client machine (work_type remote-ops), a Claude Code vs Claude Desktop vs empirica project mix-up, or where a client's identity lives (crm-mcp, not entity_registry). Triggers: '--project-id', 'which project', 'practice vs project', 'remote-ops', 'entity_registry'.

Repository
empirica ↗
Licence
MIT
Last repository change
26.10.2026

Assessment and security

90/ 100Class: good
Format25 / 25
Frontmatter with name and description, valid name, description up to 1,024 characters, name matching the folder.
Discoverability25 / 25
Description explains when to use the skill, has a reasonable length and uses third person.
Content25 / 35
At least 150 words and at most 500 lines, headings, step lists, examples or code.
Hygiene15 / 15
No placeholders such as TODO, no Windows paths, with a licence.
Riskno signals detected in the scan
Files in this package
2
Scripts
0
HTML comments
0
URLs in SKILL.md
0
Deprecation

No signals detected. Repository changed on 26.10.2026, without references to retired models or APIs.

Licence

MIT, open: use and modify while retaining author attribution.

What it does and when to use it

Use when the question is which practice or project work belongs to: writing to another practice with --project-id, reading another practice's artifacts, working on a remote or client machine (work_type remote-ops), a Claude Code vs Claude Desktop vs empirica project mix-up, or where a client's identity lives (crm-mcp, not entity_registry). Triggers: '--project-id', 'which project', 'practice vs project', 'remote-ops', 'entity_registry'.

Triggers from the description

s identity lives (crm-mcp, not entity_registry). Triggers:which projectpractice vs projectremote-opsentity_registry
Original author description

Use when the question is which practice or project work belongs to: writing to another practice with --project-id, reading another practice's artifacts, working on a remote or client machine (work_type remote-ops), a Claude Code vs Claude Desktop vs empirica project mix-up, or where a client's identity lives (crm-mcp, not entity_registry). Triggers: '--project-id', 'which project', 'practice vs project', 'remote-ops', 'entity_registry'.

How it works

  1. The practice model
Original SKILL.md headings · 59 lines, 455 words
SKILL.md preview
---
name: practice-model
description: "Use when the question is which practice or project work belongs to: writing to another practice with --project-id, reading another practice's artifacts, working on a remote or client machine (work_type remote-ops), a Claude Code vs Claude Desktop vs empirica project mix-up, or where a client's identity lives (crm-mcp, not entity_registry). Triggers: '--project-id', 'which project', 'practice vs project', 'remote-ops', 'entity_registry'."
version: 1.0.0
---

# Practice model

Load it when the answer to "where does this belong, and as whom am I acting" is not obvious from the working directory.

---

## The practice model

The prompt's IDENTITY section defines practice, practitioner and agent; the unit of identity is the practice, not the LLM, the
directory or the conversation. Two more terms matter here: a **client / contact** is an entity the practice serves, and an
**engagement** is a scoped piece of work for one. The identity and status of both live in `crm-mcp`, not in `entity_registry`.

### Entity registry as the shared substrate

`~/.empirica/workspace/workspace.db` holds an `entity_registry` of the practices
(`entity_type='project'`) and users across the org. `entity_memberships` (M:N) holds
typed relationships — `member-of`, `serves`, `uses`, `owns`.

**Organizations, contacts and engagements are not registry state any more.** Core's
CRM projection was retired (commit `fcf442110`): `crm-mcp` is the canonical store
(`empirica-workspace org|contact|engagement`, or the `crm_*` tools). Old
`organization`, `contact` and `engagement` rows may still sit in the registry; their
ids are valid join targets, but their name and status are stale. Do not read them
with `entity-show`; ask `crm-mcp`. What the practice learned about a client lives in
its own epistemic graph (`empirica-workspace entity knowledge --entity ...`).

**Vocabulary vs storage:** the table stores `entity_type='project'`; the concept is
"practice". Both are correct — one is the literal value, one is the load-bearing
idea. Future types (`ai`, `agent`, `skill`) are not populated, so don't claim them as
current state.

Walk it from any node: `entity-list` (by type/status) · `entity-show <type:id>` (one
entity plus its edges) · `entity-walk <type:id> [--depth N]` (BFS, cycle-protected) ·
`entity-search <query>`. All take `--output {human|json}`.

### When practice ≠ working directory

`.empirica/project.yaml`'s `ai_id` is canonical; filesystem location is incidental.
The Sentinel, calibration and inbox routing all follow `ai_id`.

- **SSH'd into a client's machine.** Your CWD is theirs, but you act *as* your home
  practice. Set `work_type=remote-ops` so the Sentinel reports
  `ungrounded_remote_ops` instead of scoring against an empty git tree.
- **Reading another practice's findings.** `project-search --project-id <other>
  --task "..."` reaches across. Don't `cd` over and re-bootstrap just to read.
- **Writing elsewhere.** Default to your active practice; use `--project-id <other>`
  only when you genuinely discovered something that practice owns. Switching
  practices to write one finding costs you context for the next ten. (Supported today
  on `finding-log` and `unknown-log`; other verbs need the full UUID.)

### Three things called "project"

- **Empirica practice** — the epistemic seat, identified by `ai_id`.
  Artifacts accumulate here and persist across models and moves; calibration accrues to the model that did the work.
- **Claude Code project** — a filesystem location with its own `.claude/`. Often
  one-to-one with a practice; not always.
- **Claude Desktop project** — a conversation-context bundle. Orthogonal to both.
Files in this package (2)
  • README.md 1 KB
  • SKILL.md 4 KB

Versions

The database has no other skills named practice-model.

Database snapshot: 13.11.2026 · package version f2a97f3ced83 (SHA-256 digest of the entire package)

Downloads in the last 30 days: 0 · ranking

Report a problem with this skill: harmful content, incorrect descriptions or an author’s removal request.

Similar skills

  • 90ops-research
    OPS on-demand: This skill should be used when the user asks to \"research this\", \"find the best practice…

Feedback and reports

Your message goes to Bartosz Sokoliński. An email address is needed only for a reply. See the privacy policy.