agami-model

Name: agami-model
Author: AgamiAI

19stars0forks

How to install agami-model?

agamiai/agami-core/agami-model

$npx -y skills add AgamiAI/agami-core --skill agami-model

Installs into the current project.

Summary

The single dashboard for the active profile's semantic model — browse, curate, AND sign off the trust layer in one surface. Browse every subject area, table, field, metric, entity, and join with live search; edit descriptions/metrics/entities/joins; exclude tables/columns you don

Files · 1

View on GitHub

SKILL.md

1	# agami model
2
3	You are running the unified model + trust surface — one dashboard to browse the live semantic model, curate it (exclude / edit / add), AND sign off the trust layer (approve / reject metrics, entities, joins). It replaces the separate model-explorer and review-dashboard surfaces.
4
5	This skill orchestrates:
6
7	1. Render — invoke `render_model_explorer.py` to walk every YAML and write a self-contained HTML artifact at `<artifacts_dir>/local/model/<profile>/<ts>.html`. The Python script does the YAML reading — no LLM tokens spent on the walk. The dashboard has tabs: Organization · Review · Subject areas · Tables · Metrics · Entities · Joins · Examples · Queued. The Review tab is the sign-off queue (the old `/agami-review`); pass `--initial-tab review` to open on it.
8	2. Open + wait — auto-open the file, end the turn, wait for the user to come back with a "Generate feedback for Claude" block (exclude/include, approve/reject, edits, new metrics, org edit).
9	3. Apply — for each batch, run `semantic_model.cli curate` with an ops JSON. The engine flips review_state / stamps sign-off, runs the validator, reverts via git on failure, appends to `curation_log.jsonl`, and commits.
10	4. Re-render — render to a new timestamped file and re-open. Wait for the next batch.
11
12	Trust-spine semantics — three actions on the same `review_state` field:
13	- Exclude / Reject → `rejected`. The loader drops rejected tables, columns, metrics, entities, and relationships entirely (`include_rejected=False` at runtime) — never in prompts, never joined, never aggregated. ("Exclude" is the verb for tables/columns; "Reject" for metrics/entities/joins — same op.)
14	- Include → back to `unreviewed`.
15	- Approve → `approved` + a sign-off stamp (`signed_off_by`/`_at`/`_role`). Rule 1 (metrics) — a query that uses an unsigned metric still answers but carries a "not signed off" warning on its receipt until it's approved; Rule 2 (entities, inferred joins) is usable while unreviewed and self-approves through use. Only `rejected` entries are dropped from the runtime entirely. Approving requires the curator's email + role (Phase 0) — the validator rejects an approved entry with no sign-off stamp.
16
17	## Conversation style
18
19	- Tight loops. The dashboard is the surface; the chat is just the input channel.
20	- Don't restate the dashboard in chat. A successful apply gets a one-line ack with the count and the new file path.
21	- Qualified names everywhere. Tables are `<area>.<table>`. Columns are `<area>.<table>.<column>` (area = subject area). No bare names.
22
23	---
24
25	## Phase 0: Preflight
26
27	- Plan-mode check — this skill writes YAMLs. If plan mode is active, refuse: "I can't apply model edits in plan mode — switch to Auto* or Edit Automatically mode (Shift+Tab to cycle) and re-invoke. (You can still inspect a previously-rendered dashboard at `<artifacts_dir>/local/model/<profile>/<ts>.html`.)"* Do NOT write a plan file. Do NOT call `ExitPlanMode`.
28	- Resolve `<profile>` and `<artifacts_dir>` via the standard chain (`AGAMI_PROFILE` → `<artifacts_dir>/local/.config.active_profile` → `default`; `AGAMI_ARTIFACTS_DIR` → `.config.artifacts_dir` → `~/agami-artifacts`).
29	- A pasted feedback block names its own target. When applying a

People who liked this also viewed

6 picks

Type

agami-model

19stars0forks

View on GitHub

How to install agami-model?

agamiai/agami-core/agami-model

$npx -y skills add AgamiAI/agami-core --skill agami-model

Installs into the current project.

Summary

Files · 1

View on GitHub

SKILL.md

1	# agami model
2
3	You are running the unified model + trust surface — one dashboard to browse the live semantic model, curate it (exclude / edit / add), AND sign off the trust layer (approve / reject metrics, entities, joins). It replaces the separate model-explorer and review-dashboard surfaces.
4
5	This skill orchestrates:
6
7	1. Render — invoke `render_model_explorer.py` to walk every YAML and write a self-contained HTML artifact at `<artifacts_dir>/local/model/<profile>/<ts>.html`. The Python script does the YAML reading — no LLM tokens spent on the walk. The dashboard has tabs: Organization · Review · Subject areas · Tables · Metrics · Entities · Joins · Examples · Queued. The Review tab is the sign-off queue (the old `/agami-review`); pass `--initial-tab review` to open on it.
8	2. Open + wait — auto-open the file, end the turn, wait for the user to come back with a "Generate feedback for Claude" block (exclude/include, approve/reject, edits, new metrics, org edit).
9	3. Apply — for each batch, run `semantic_model.cli curate` with an ops JSON. The engine flips review_state / stamps sign-off, runs the validator, reverts via git on failure, appends to `curation_log.jsonl`, and commits.
10	4. Re-render — render to a new timestamped file and re-open. Wait for the next batch.
11
12	Trust-spine semantics — three actions on the same `review_state` field:
13	- Exclude / Reject → `rejected`. The loader drops rejected tables, columns, metrics, entities, and relationships entirely (`include_rejected=False` at runtime) — never in prompts, never joined, never aggregated. ("Exclude" is the verb for tables/columns; "Reject" for metrics/entities/joins — same op.)
14	- Include → back to `unreviewed`.
15	- Approve → `approved` + a sign-off stamp (`signed_off_by`/`_at`/`_role`). Rule 1 (metrics) — a query that uses an unsigned metric still answers but carries a "not signed off" warning on its receipt until it's approved; Rule 2 (entities, inferred joins) is usable while unreviewed and self-approves through use. Only `rejected` entries are dropped from the runtime entirely. Approving requires the curator's email + role (Phase 0) — the validator rejects an approved entry with no sign-off stamp.
16
17	## Conversation style
18
19	- Tight loops. The dashboard is the surface; the chat is just the input channel.
20	- Don't restate the dashboard in chat. A successful apply gets a one-line ack with the count and the new file path.
21	- Qualified names everywhere. Tables are `<area>.<table>`. Columns are `<area>.<table>.<column>` (area = subject area). No bare names.
22
23	---
24
25	## Phase 0: Preflight
26
27	- Plan-mode check — this skill writes YAMLs. If plan mode is active, refuse: "I can't apply model edits in plan mode — switch to Auto* or Edit Automatically mode (Shift+Tab to cycle) and re-invoke. (You can still inspect a previously-rendered dashboard at `<artifacts_dir>/local/model/<profile>/<ts>.html`.)"* Do NOT write a plan file. Do NOT call `ExitPlanMode`.
28	- Resolve `<profile>` and `<artifacts_dir>` via the standard chain (`AGAMI_PROFILE` → `<artifacts_dir>/local/.config.active_profile` → `default`; `AGAMI_ARTIFACTS_DIR` → `.config.artifacts_dir` → `~/agami-artifacts`).
29	- A pasted feedback block names its own target. When applying a

People who liked this also viewed

6 picks

Type