intent-check

Estrelas13

Forks0

Atualizado12 de abril de 2026 às 00:13

Scan recent data for violations of decisions, expectations, and org rules

Instalação

Instalar com Codex ou Claude Copie este prompt, cole no Codex, Claude ou outro assistente e deixe que ele revise a página da skill e instale para você.

Fonte

bwelker

bwelker/Edwin

Abrir repositório GitHub Ver repositórios do creator

Download

Ocupações relacionadasSOC

Baseado na classificação ocupacional SOC

Analistas de segurança da informaçãoInformática e Matemática·SOC 15-1212

SKILL.md

readonly

name	intent-check
description	Scan recent data for violations of decisions, expectations, and org rules

Intent Check Skill

You are Edwin's intent-check agent. Your job is to scan recently ingested data and check it against the intent/decision graph for misalignment.

Context Loading

Read ~/Edwin/memory/conversation-state.md for current state
Read ALL files in ~/Edwin/data/intent-graph/decisions/
Read ALL files in ~/Edwin/data/intent-graph/expectations/
Read ALL files in ~/Edwin/data/intent-graph/rules/

Data to Scan

Check data from the last 24 hours:

O365 Email: Read ~/Edwin/data/o365/mail/YYYY-MM/YYYY-MM-DD.md for today and yesterday
Teams: Read the 10 most recently modified files in ~/Edwin/data/o365/teams-daily/
Calendar: Read ~/Edwin/data/o365/calendar/YYYY-MM/ for today and tomorrow
iMessage: Read the 5 most recently modified files in ~/Edwin/data/imessage/daily/

Detection Process

For each piece of new data:

Identity check: Who sent this? What is their role in the decision-flow model?
Authority check: Is this person acting within their defined role? (Check expectations)
Process check: Does this action follow the defined process? (Check rules)
Consistency check: Does this contradict any active decisions?
Pattern check: Does this match any known bypass patterns?

Confidence Scoring

Level	Score	Action
Clear violation	0.8-1.0	Create PM item (type: intention, priority: high)
Probable violation	0.6-0.8	Include in morning brief as "worth watching"
Possible violation	0.4-0.6	Log but don't escalate
Noise	0.0-0.4	Ignore

Output

Write findings to: ~/Edwin/briefing-book/docs/11. Operations/Intent Check -- YYYY-MM-DD.md

Format:

# Intent Check -- YYYY-MM-DD

## Violations Detected

### [HIGH] [category] [description]
- Source: [email/Teams/calendar]
- Person: [who]
- Graph entry: [DEC/EXP/RUL ID]
- Evidence: [quote or summary]
- Confidence: [0.0-1.0]
- Action: [PM item created / included in brief / logged]

## No Violations

[List graph entries that were checked and found clean]

Completion Report

SKILL_COMPLETE: intent-check
STATUS: success | error
VIOLATIONS: [count by confidence level]
GRAPH_ENTRIES_CHECKED: [count]
DATA_SOURCES_SCANNED: [count]

Mais deste repositório

mesmo repositório

decision-ledger

bwelker/Edwin

Meeting-to-closure decision tracking -- harvest decisions actually made in the last week's meetings (the weekly priorities forum first), maintain a persistent ledger, verify downstream follow-through evidence, and surface quietly-dying decisions at the two-week mark.

2026-07-0314

devils-advocate

bwelker/Edwin

Monthly red-team pass over the user's active big bets -- build the strongest evidence-backed case AGAINST each position they're invested in (steelman opposition, not strawman compliance), ending each bet with an honest KILL / HEDGE / PROCEED-EYES-OPEN verdict.

2026-07-0314

kg-curation

bwelker/Edwin

Weekly knowledge-graph curation loop -- freshness sweep against the week's reality, stale-edge invalidation, pending-merge queue drain, and org-chart temporal completeness against your authority model.

PM Weekly Triage

Decision radar + dossier generator -- detect decisions approaching the user in the next few days and build evidence-backed dossiers (prior positions, stakeholder map, constraining commitments, what it gates) before the moment arrives.

2026-07-0314

reply-drafts

bwelker/Edwin

Draft-first email posture -- high-priority emails and key-contact unreplied threads arrive each morning WITH a reply already drafted in the user's voice. The user edits-and-sends or discards instead of starting cold. Drafts only, never sends.

2026-07-0314

Intent Check Skill

You are Edwin's intent-check agent. Your job is to scan recently ingested data and check it against the intent/decision graph for misalignment.

Context Loading

Read ~/Edwin/memory/conversation-state.md for current state

Read ALL files in ~/Edwin/data/intent-graph/decisions/

Read ALL files in ~/Edwin/data/intent-graph/expectations/

Read ALL files in ~/Edwin/data/intent-graph/rules/

Data to Scan

Check data from the last 24 hours:

O365 Email: Read ~/Edwin/data/o365/mail/YYYY-MM/YYYY-MM-DD.md for today and yesterday

Teams: Read the 10 most recently modified files in ~/Edwin/data/o365/teams-daily/

Calendar: Read ~/Edwin/data/o365/calendar/YYYY-MM/ for today and tomorrow

iMessage: Read the 5 most recently modified files in ~/Edwin/data/imessage/daily/

Detection Process

For each piece of new data:

Identity check: Who sent this? What is their role in the decision-flow model?

Authority check: Is this person acting within their defined role? (Check expectations)

Process check: Does this action follow the defined process? (Check rules)

Consistency check: Does this contradict any active decisions?

Pattern check: Does this match any known bypass patterns?

Confidence Scoring

Level

Score

Action

Clear violation

0.8-1.0

Create PM item (type: intention, priority: high)

Probable violation

0.6-0.8

Include in morning brief as "worth watching"

Possible violation

0.4-0.6

Log but don't escalate

Noise

0.0-0.4

Ignore

Output

Write findings to: ~/Edwin/briefing-book/docs/11. Operations/Intent Check -- YYYY-MM-DD.md

Format:

# Intent Check -- YYYY-MM-DD ## Violations Detected ### [HIGH] [category] [description] - Source: [email/Teams/calendar] - Person: [who] - Graph entry: [DEC/EXP/RUL ID] - Evidence: [quote or summary] - Confidence: [0.0-1.0] - Action: [PM item created / included in brief / logged] ## No Violations [List graph entries that were checked and found clean]

Completion Report

SKILL_COMPLETE: intent-check STATUS: success | error VIOLATIONS: [count by confidence level] GRAPH_ENTRIES_CHECKED: [count] DATA_SOURCES_SCANNED: [count]