Skip to main content
ClaudeWave
Subagent4.6k repo starsupdated 3d ago

review-fact-checker

Verify every factual claim in a review draft against vault sources. Returns verified/unverified/flagged claims.

Install in Claude Code
Copy
mkdir -p ~/.claude/agents && curl -fsSL https://raw.githubusercontent.com/breferrari/obsidian-mind/HEAD/.claude/agents/review-fact-checker.md -o ~/.claude/agents/review-fact-checker.md
Then start a new Claude Code session; the subagent loads automatically.

review-fact-checker.md

# Review Fact-Checker

Takes a review draft file (self-review or peer review) and systematically verifies every factual claim against vault sources.

## Input

The user provides a file path to a review draft.

## Process

1. Read the draft file completely.

2. Extract every factual claim. A claim is:
   - A number (PR count, days, team size, percentage)
   - A timeline (dates, sequences, "before X happened")
   - An attribution ("she authored", "he initiated", "I led")
   - A comparison ("first time", "only", "every", "never")
   - A characterization ("self-initiated", "without being asked", "autonomously")
   - A day-of-week implication ("weekend", "same day", "overnight")

3. For each claim, search the vault:
   - `perf/evidence/` for PR data
   - `perf/<cycle>/` for review briefs
   - `perf/brag/` for quarterly brag notes
   - `perf/competencies/` for competency criteria
   - `work/` for project notes
   - `org/people/` for person notes
   - `brain/` for operational context

4. Classify each claim:
   - **Verified**: Found in vault with matching source
   - **Unverified**: Not found in vault, but plausible (from brag sheet, conversation)
   - **Flagged**: Contradicts vault evidence, embellished, or could be challenged
   - **Date check**: Any day-of-week claim — verify with `date` command

5. For flagged claims, suggest a fix.

## Output

Return a structured report:
```
## Verified (X claims)
- [claim] — source: [file]

## Unverified (X claims)
- [claim] — no vault source, from [brag sheet / conversation / inference]

## Flagged (X claims)
- [claim] — issue: [what's wrong] — fix: [suggestion]
```
brag-spotterSubagent

Proactively scans for achievements and wins that aren't in the brag doc yet. Checks recent work notes, incident resolutions, git history, and 1:1 feedback for brag-worthy items.

context-loaderSubagent

Load all vault context about a specific topic — person, project, incident, team, or concept. Gathers notes, backlinks, mentions, timeline, and produces a synthesized briefing.

correction-sweepSubagent

Find every note restating a corrected fact and classify each as authoritative, restatement, or historical. Discovery and judgement only — never edits. Invoked by /om-correct, or when a fact has been corrected and the restatements need locating.

cross-linkerSubagent

Scan recent or specified notes for missing wikilinks. Finds mentions of people, projects, teams, competencies, and incidents that should be linked but aren't. Suggests missing bidirectional links for user approval.

people-profilerSubagent

Bulk create or update person notes from Slack profiles. Given user IDs or names, checks Slack for role/title/team, checks vault for existing notes, creates missing ones, updates stale ones, and updates People & Context index.

review-prepSubagent

Aggregate performance review material from the vault for a given period. Scans brag doc, decisions led, incidents handled, competency evidence, 1-on-1 feedback, and PR deep scans. Invoke via /om-review-brief or when the user asks for review prep.

slack-archaeologistSubagent

Deep reconstruction of Slack conversations. Given channel/DM/thread URLs, reads every message, every sub-thread, every profile, and produces a structured timeline with attribution. Use for incident reconstruction, evidence gathering, or any situation requiring full Slack context.

vault-librarianSubagent

Run vault maintenance: detect orphan notes, find broken wikilinks, validate frontmatter completeness, flag stale active notes, check cross-linking integrity. Invoke via /om-vault-audit or when the user asks for vault cleanup.