/matter-intake
- Load
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → risk calibration (for triage), landscape (for context, conflicts method), stakeholders (for who to loop in).
- Follow the workflow and reference below.
- Run the uniform intake: identification, conflicts check, source, risk triage, materiality, outside counsel, internal owners, legal hold, key dates, initial posture.
- Generate slug from matter name (lowercase, hyphens, year).
- Create
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/matter.md — full narrative intake.
- Create
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/history.md — seeded with the intake as the first entry.
- Append structured row to
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml.
- Confirm with the user: "Here's the row I'll write — any edits?"
Matter Intake
Purpose
Every new matter goes through the same intake so the portfolio stays comparable. Uniform rows in _log.yaml let the status skill roll up. Narrative in matter.md captures what the row can't. History file seeded here becomes the event record.
Load context
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md — risk calibration (triage thresholds, materiality, settlement ladder), landscape (stakeholders, outside counsel bench).
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml — to confirm slug uniqueness.
The intake
1. Identification
- Matter name (as commonly referenced, e.g., "Acme v. Us 2026")
- Counterparty
- Matter type:
contract | employment | ip | regulatory | investigation | product | other
- Our role:
plaintiff | defendant | claimant | respondent | investigated
- If the practice profile's
## Side is plaintiff, defense, or a "both — default X" variant, pre-fill the role from that default and confirm. If ## Side is varies by matter, ask cold. Never silently assume a posture the practice profile hasn't set.
- The role drives downstream skills: plaintiff-posture matters route risk triage to case value / contingency economics; defense-posture matters route to exposure / reserves / insurance tender.
- Jurisdiction (court, arbitration forum, or regulatory body)
2. Conflicts check
Before going further, run the conflicts step per ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md → Conflicts clearance.
- Status:
cleared | pending | not-run | waived
- Method: match what
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md declares (corporate-legal | outside-counsel | system-check | informal | other). If the declared method is informal, say so — the record still captures that a counsel's-judgment check was the basis.
- Cleared by: name / team / firm
- Cleared date: YYYY-MM-DD
- Checked against: brief list of the specific names/entities run (counterparty, known affiliates, adverse counsel if known, key witnesses). Thin is fine; "no" is not.
- Notes: anything flagged but cleared (e.g., "Smith on our board sat on counterparty's board 2019–2021 — cleared as non-overlapping to this matter").
Behavior by status:
cleared → proceed.
pending → proceed with intake; flag prominently in matter.md and in the log row that conflicts are outstanding; surface again on every /matter-update and in /portfolio-status until resolved.
waived → rare; requires a conflict-waiver rationale (writing the waiver is outside this skill — capture that one exists, who signed it, and where it lives).
not-run → STOP. This is a gate. The skill will not create matter.md, history.md, or a _log.yaml entry until the conflicts posture is resolved. Three acceptable paths:
Path 1 — Run conflicts now. Pause this intake. Clear per ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md Conflicts clearance. Return with status: cleared or status: waived with rationale.
Path 2 — Mark pending with owner + due date. Allowed only when ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md Conflicts clearance declares parallel-intake acceptable. Capture: who is running conflicts, when they're expected to return, what entities they're checking. Intake proceeds; matter row carries conflicts.status: pending; /portfolio-status flags it every run; /matter-update re-prompts until resolved.
Path 3 — Bypass with documented rationale. Only if the user explicitly acknowledges the bypass. Record in conflicts.override:
conflicts:
status: not-run # preserved as-is
override:
by: [user name]
date: [YYYY-MM-DD]
rationale: [why conflicts were bypassed — permanent record; does not auto-expire]
This field is visible in every /portfolio-status, every /matter briefing, and every /matter-update until removed. It is never removed by the skill — only by explicit user edit to _log.yaml after conflicts are actually cleared.
Do not proceed silently. "I'll do it later" is not an acceptable response. One of Path 1/2/3 must be chosen, and the choice is captured in the record.
This step is not about the skill deciding whether a conflict exists — that's the user's/firm's judgment. It's about making sure the check happened and the record reflects it.
3. Source
How did this arrive?
demand-letter | complaint-served | subpoena | regulator-inquiry | internal-report | pre-suit-threat
- Seed doc opportunity: "If you have the initiating document (complaint, demand, subpoena), attach or share the path. It sharpens the intake."
4. Risk triage — against house calibration
- Severity: high | medium | low (reference the
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md severity bands)
- Likelihood: high | medium | low (reference the
~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md likelihood bands)
- Resulting risk rating (per the matrix): high | medium | low | critical
- Damages exposure range (best estimate)
- Non-monetary exposure (injunction? consent decree? publicity? precedent?)
If the risk calibration in ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md is thin, don't fake precision. Use the user's gut and note the thinness.
5. Materiality
Against the house thresholds in ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md:
reserved | disclosed | monitored | none
- If
reserved: reserve amount and whether finance has been notified
- If
disclosed: filing and footnote location
6. Outside counsel
- Firm
- Lead partner
- Lead partner email (used by
/oc-status to draft status requests)
- Engagement letter status:
signed | pending | none
- Budget authorization: amount and approver
- Seed doc opportunity: "Engagement letter path, if signed."
If risk is medium or higher and no outside counsel is assigned — flag it.
7. Internal owners
From ~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md landscape — which internal stakeholders are involved?
- Business lead
- HR partner (if employment)
- Comms contact (if reputational risk)
- CISO (if data or cyber)
- Other
8. Legal hold
- Issued? If yes: date, scope, custodians (list of names).
- Next refresh date (default: six months from issuance; adjust per matter).
- If no and this is active litigation or reasonably anticipated: flag urgently; offer to run
/litigation-legal:legal-hold [slug] --issue after intake completes.
- Seed doc opportunity: "Hold notice, if issued."
9. Key dates
- Response deadline (answer, objection, opposition)
- Next hearing / conference
- Statute of limitations cutoff (if applicable)
- Any regulatory deadlines
10. Initial posture
One-paragraph theory:
- What's our story?
- What's theirs?
- What's the pivot fact?
- Initial posture:
fight | settle | investigate | wait
Writing the outputs
Slug
Lowercase, hyphens, year at the end. Examples: acme-v-us-2026, employment-smith-2026, ftc-inquiry-2026.
Confirm slug is unique in _log.yaml before writing.
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/matter.md
[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
# [Matter Name]
**Slug:** [slug]
**Opened:** [YYYY-MM-DD]
**Our role:** [plaintiff/defendant/etc.]
**Status:** [status]
---
## Identification
[counterparty, jurisdiction, matter type, source]
## Conflicts
**Status:** [cleared / pending / not-run / waived]
**Method:** [corporate-legal / outside-counsel / system-check / informal / other]
**Cleared by:** [name]
**Cleared date:** [YYYY-MM-DD]
**Checked against:** [entities run]
**Notes:** [any flags cleared, waiver reference if applicable]
## Risk triage
**Severity:** [band] — [why, with reference to house severity definitions]
**Likelihood:** [band] — [why]
**Risk rating:** [high/medium/low/critical]
**Exposure:** [dollar range + non-monetary]
## Materiality
[reserved/disclosed/monitored/none — with reserve amount, disclosure location, or reasoning if "none"]
## Outside counsel
[firm, lead, engagement status, budget]
## Internal owners
[stakeholders and why each is involved]
## Legal hold
[status, date, scope]
## Key dates
[list]
## Initial theory
[one paragraph: our story, their story, pivot fact, initial posture] `[SME VERIFY — theory at intake is a working hypothesis; confirm with outside counsel before any filing or material communication that assumes this framing]`
## Open questions
[anything not yet known that matters — e.g., "insurance tender pending", "unclear whether we have coverage for X"]
---
## Seed documents
| Doc | Path / pointer |
|---|---|
| [e.g., complaint] | [path or "not yet shared"] |
~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/history.md
Seed the history file with the intake as entry zero:
# History: [Matter Name]
Append-only event log. Most recent at top.
---
## [YYYY-MM-DD] — Matter opened
[Source, who brought it in, initial triage summary, outside counsel assigned, legal hold issued yes/no.]
Append to ~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml
Add a row per the schema. Example:
- id: acme-v-us-2026
name: "Acme Corp v. Company"
type: contract
role: defendant
counterparty: "Acme Corp"
jurisdiction: "N.D. Cal."
# status is derived from source:
# source: pre-suit-threat | demand-letter → status: threatened
# source: complaint-served | subpoena | regulator-inquiry → status: active
# source: internal-report → status: threatened (default) or active if formal process has started
status: active
stage: pleadings
source: complaint-served
outside_counsel:
firm: "Wilson Sonsini"
lead: "J. Reyes"
email: "jreyes@wsgr.example.com"
engagement: signed
conflicts:
status: cleared
method: corporate-legal
cleared_by: "K. Patel"
cleared_date: 2026-04-20
override: # populated only on Path 3 bypass
by: null
date: null
rationale: null
risk: high
materiality: reserved
exposure_range: "$2M–$5M"
internal_owners:
business_lead: "Jane Smith"
hr_partner: null
comms_contact: null
legal_hold:
issued: true
issued_date: 2026-02-15
scope: "Sales org 2023–2026"
custodians: ["Jane Smith", "R. Chen", "T. Patel"]
last_refresh: 2026-02-15
next_refresh: 2026-08-15
released: null
related_matters: []
opened: 2026-04-20
next_deadline: 2026-05-15
last_updated: 2026-04-20
path: matters/acme-v-us-2026/
Confirm before writing
Show the user the row and the matter.md content:
Here's what I'll write. Flag anything wrong or thin before I commit.
Close with the next-steps decision tree
End with the next-steps decision tree per CLAUDE.md ## Outputs. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.
What this skill does not do
- Run the conflicts check itself. It records the result, status, method, and the entities checked. The actual clearance happens in whatever system (or judgment) the house practice profile declares. If the user says "cleared," the skill takes that at face value and captures the metadata.
- Decide the initial theory. It captures what the user says; it doesn't invent one.
- Issue the legal hold. Flags it if missing. User issues it.
1---
2name: matter-intake
3description: Intake a new matter — uniform questions covering identification, conflicts, source, risk triage, materiality, outside counsel, owners, legal hold, and key dates; writes matter.md and history.md and appends a structured row to _log.yaml. Use when the user says "new matter", "intake this matter", or wants to bring a new matter into the portfolio.
4argument-hint: "[optional matter name]"
5metadata:
6 source: https://skillmd.com/skills/anthropics-claude-for-legal/matter-intake
7---
8
9# /matter-intake
10
111. Load `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → risk calibration (for triage), landscape (for context, conflicts method), stakeholders (for who to loop in).
122. Follow the workflow and reference below.
133. Run the uniform intake: identification, conflicts check, source, risk triage, materiality, outside counsel, internal owners, legal hold, key dates, initial posture.
144. Generate slug from matter name (lowercase, hyphens, year).
155. Create `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/matter.md` — full narrative intake.
166. Create `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/history.md` — seeded with the intake as the first entry.
177. Append structured row to `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml`.
188. Confirm with the user: "Here's the row I'll write — any edits?"
19
20---
21
22# Matter Intake
23
24## Purpose
25
26Every new matter goes through the same intake so the portfolio stays comparable. Uniform rows in `_log.yaml` let the status skill roll up. Narrative in `matter.md` captures what the row can't. History file seeded here becomes the event record.
27
28## Load context
29
30- `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` — risk calibration (triage thresholds, materiality, settlement ladder), landscape (stakeholders, outside counsel bench).
31- `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml` — to confirm slug uniqueness.
32
33## The intake
34
35### 1. Identification
36
37- Matter name (as commonly referenced, e.g., "Acme v. Us 2026")
38- Counterparty
39- Matter type: `contract | employment | ip | regulatory | investigation | product | other`
40- Our role: `plaintiff | defendant | claimant | respondent | investigated`
41 - If the practice profile's `## Side` is `plaintiff`, `defense`, or a "both — default X" variant, pre-fill the role from that default and confirm. If `## Side` is `varies by matter`, ask cold. Never silently assume a posture the practice profile hasn't set.
42 - The role drives downstream skills: plaintiff-posture matters route risk triage to case value / contingency economics; defense-posture matters route to exposure / reserves / insurance tender.
43- Jurisdiction (court, arbitration forum, or regulatory body)
44
45### 2. Conflicts check
46
47Before going further, run the conflicts step per `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` → Conflicts clearance.
48
49- **Status:** `cleared | pending | not-run | waived`
50- **Method:** match what `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` declares (`corporate-legal | outside-counsel | system-check | informal | other`). If the declared method is `informal`, say so — the record still captures that a counsel's-judgment check was the basis.
51- **Cleared by:** name / team / firm
52- **Cleared date:** YYYY-MM-DD
53- **Checked against:** brief list of the specific names/entities run (counterparty, known affiliates, adverse counsel if known, key witnesses). Thin is fine; "no" is not.
54- **Notes:** anything flagged but cleared (e.g., "Smith on our board sat on counterparty's board 2019–2021 — cleared as non-overlapping to this matter").
55
56Behavior by status:
57
58- `cleared` → proceed.
59- `pending` → proceed with intake; flag prominently in `matter.md` and in the log row that conflicts are outstanding; surface again on every `/matter-update` and in `/portfolio-status` until resolved.
60- `waived` → rare; requires a conflict-waiver rationale (writing the waiver is outside this skill — capture that one exists, who signed it, and where it lives).
61- `not-run` → **STOP. This is a gate.** The skill will not create `matter.md`, `history.md`, or a `_log.yaml` entry until the conflicts posture is resolved. Three acceptable paths:
62
63 **Path 1 — Run conflicts now.** Pause this intake. Clear per `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` Conflicts clearance. Return with `status: cleared` or `status: waived` with rationale.
64
65 **Path 2 — Mark pending with owner + due date.** Allowed only when `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` Conflicts clearance declares parallel-intake acceptable. Capture: who is running conflicts, when they're expected to return, what entities they're checking. Intake proceeds; matter row carries `conflicts.status: pending`; `/portfolio-status` flags it every run; `/matter-update` re-prompts until resolved.
66
67 **Path 3 — Bypass with documented rationale.** Only if the user explicitly acknowledges the bypass. Record in `conflicts.override`:
68
69 ```yaml
70 conflicts:
71 status: not-run # preserved as-is
72 override:
73 by: [user name]
74 date: [YYYY-MM-DD]
75 rationale: [why conflicts were bypassed — permanent record; does not auto-expire]
76 ```
77
78 This field is visible in every `/portfolio-status`, every `/matter` briefing, and every `/matter-update` until removed. It is never removed by the skill — only by explicit user edit to `_log.yaml` after conflicts are actually cleared.
79
80 **Do not proceed silently.** "I'll do it later" is not an acceptable response. One of Path 1/2/3 must be chosen, and the choice is captured in the record.
81
82This step is not about the skill deciding whether a conflict exists — that's the user's/firm's judgment. It's about making sure the check happened and the record reflects it.
83
84### 3. Source
85
86How did this arrive?
87- `demand-letter | complaint-served | subpoena | regulator-inquiry | internal-report | pre-suit-threat`
88- *Seed doc opportunity:* "If you have the initiating document (complaint, demand, subpoena), attach or share the path. It sharpens the intake."
89
90### 4. Risk triage — against house calibration
91
92- Severity: high | medium | low (reference the `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` severity bands)
93- Likelihood: high | medium | low (reference the `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` likelihood bands)
94- Resulting risk rating (per the matrix): high | medium | low | critical
95- Damages exposure range (best estimate)
96- Non-monetary exposure (injunction? consent decree? publicity? precedent?)
97
98If the risk calibration in `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` is thin, don't fake precision. Use the user's gut and note the thinness.
99
100### 5. Materiality
101
102Against the house thresholds in `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md`:
103- `reserved | disclosed | monitored | none`
104- If `reserved`: reserve amount and whether finance has been notified
105- If `disclosed`: filing and footnote location
106
107### 6. Outside counsel
108
109- Firm
110- Lead partner
111- **Lead partner email** (used by `/oc-status` to draft status requests)
112- Engagement letter status: `signed | pending | none`
113- Budget authorization: amount and approver
114- *Seed doc opportunity:* "Engagement letter path, if signed."
115
116If risk is medium or higher and no outside counsel is assigned — flag it.
117
118### 7. Internal owners
119
120From `~/.claude/plugins/config/claude-for-legal/litigation-legal/CLAUDE.md` landscape — which internal stakeholders are involved?
121- Business lead
122- HR partner (if employment)
123- Comms contact (if reputational risk)
124- CISO (if data or cyber)
125- Other
126
127### 8. Legal hold
128
129- Issued? If yes: date, scope, custodians (list of names).
130- Next refresh date (default: six months from issuance; adjust per matter).
131- If no and this is active litigation or reasonably anticipated: flag urgently; offer to run `/litigation-legal:legal-hold [slug] --issue` after intake completes.
132- *Seed doc opportunity:* "Hold notice, if issued."
133
134### 9. Key dates
135
136- Response deadline (answer, objection, opposition)
137- Next hearing / conference
138- Statute of limitations cutoff (if applicable)
139- Any regulatory deadlines
140
141### 10. Initial posture
142
143One-paragraph theory:
144- What's our story?
145- What's theirs?
146- What's the pivot fact?
147- Initial posture: `fight | settle | investigate | wait`
148
149## Writing the outputs
150
151### Slug
152
153Lowercase, hyphens, year at the end. Examples: `acme-v-us-2026`, `employment-smith-2026`, `ftc-inquiry-2026`.
154
155Confirm slug is unique in `_log.yaml` before writing.
156
157### `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/matter.md`
158
159```markdown
160[WORK-PRODUCT HEADER — per plugin config ## Outputs — differs by role; see `## Who's using this`]
161
162# [Matter Name]
163
164**Slug:** [slug]
165**Opened:** [YYYY-MM-DD]
166**Our role:** [plaintiff/defendant/etc.]
167**Status:** [status]
168
169---
170
171## Identification
172
173[counterparty, jurisdiction, matter type, source]
174
175## Conflicts
176
177**Status:** [cleared / pending / not-run / waived]
178**Method:** [corporate-legal / outside-counsel / system-check / informal / other]
179**Cleared by:** [name]
180**Cleared date:** [YYYY-MM-DD]
181**Checked against:** [entities run]
182**Notes:** [any flags cleared, waiver reference if applicable]
183
184## Risk triage
185
186**Severity:** [band] — [why, with reference to house severity definitions]
187**Likelihood:** [band] — [why]
188**Risk rating:** [high/medium/low/critical]
189**Exposure:** [dollar range + non-monetary]
190
191## Materiality
192
193[reserved/disclosed/monitored/none — with reserve amount, disclosure location, or reasoning if "none"]
194
195## Outside counsel
196
197[firm, lead, engagement status, budget]
198
199## Internal owners
200
201[stakeholders and why each is involved]
202
203## Legal hold
204
205[status, date, scope]
206
207## Key dates
208
209[list]
210
211## Initial theory
212
213[one paragraph: our story, their story, pivot fact, initial posture] `[SME VERIFY — theory at intake is a working hypothesis; confirm with outside counsel before any filing or material communication that assumes this framing]`
214
215## Open questions
216
217[anything not yet known that matters — e.g., "insurance tender pending", "unclear whether we have coverage for X"]
218
219---
220
221## Seed documents
222
223| Doc | Path / pointer |
224|---|---|
225| [e.g., complaint] | [path or "not yet shared"] |
226```
227
228### `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/[slug]/history.md`
229
230Seed the history file with the intake as entry zero:
231
232```markdown
233# History: [Matter Name]
234
235Append-only event log. Most recent at top.
236
237---
238
239## [YYYY-MM-DD] — Matter opened
240
241[Source, who brought it in, initial triage summary, outside counsel assigned, legal hold issued yes/no.]
242```
243
244### Append to `~/.claude/plugins/config/claude-for-legal/litigation-legal/matters/_log.yaml`
245
246Add a row per the schema. Example:
247
248```yaml
249- id: acme-v-us-2026
250 name: "Acme Corp v. Company"
251 type: contract
252 role: defendant
253 counterparty: "Acme Corp"
254 jurisdiction: "N.D. Cal."
255 # status is derived from source:
256 # source: pre-suit-threat | demand-letter → status: threatened
257 # source: complaint-served | subpoena | regulator-inquiry → status: active
258 # source: internal-report → status: threatened (default) or active if formal process has started
259 status: active
260 stage: pleadings
261 source: complaint-served
262 outside_counsel:
263 firm: "Wilson Sonsini"
264 lead: "J. Reyes"
265 email: "jreyes@wsgr.example.com"
266 engagement: signed
267 conflicts:
268 status: cleared
269 method: corporate-legal
270 cleared_by: "K. Patel"
271 cleared_date: 2026-04-20
272 override: # populated only on Path 3 bypass
273 by: null
274 date: null
275 rationale: null
276 risk: high
277 materiality: reserved
278 exposure_range: "$2M–$5M"
279 internal_owners:
280 business_lead: "Jane Smith"
281 hr_partner: null
282 comms_contact: null
283 legal_hold:
284 issued: true
285 issued_date: 2026-02-15
286 scope: "Sales org 2023–2026"
287 custodians: ["Jane Smith", "R. Chen", "T. Patel"]
288 last_refresh: 2026-02-15
289 next_refresh: 2026-08-15
290 released: null
291 related_matters: []
292 opened: 2026-04-20
293 next_deadline: 2026-05-15
294 last_updated: 2026-04-20
295 path: matters/acme-v-us-2026/
296```
297
298## Confirm before writing
299
300Show the user the row and the matter.md content:
301
302> Here's what I'll write. Flag anything wrong or thin before I commit.
303
304## Close with the next-steps decision tree
305
306End with the next-steps decision tree per CLAUDE.md `## Outputs`. Customize the options to what this skill just produced — the five default branches (draft the X, escalate, get more facts, watch and wait, something else) are a starting point, not a lock-in. The tree is the output; the lawyer picks.
307
308## What this skill does not do
309
310- **Run the conflicts check itself.** It records the result, status, method, and the entities checked. The actual clearance happens in whatever system (or judgment) the house practice profile declares. If the user says "cleared," the skill takes that at face value and captures the metadata.
311- Decide the initial theory. It captures what the user says; it doesn't invent one.
312- Issue the legal hold. Flags it if missing. User issues it.