synthesize
Analyst procedure — read verified findings + relationships and propose new edges and new leads.
Skill by abedegno
Chalk Labs
Need help deploying synthesize?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/abedegno-synthesize
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/synthesize
What's inside
- Skill name
synthesize- Description
- Analyst procedure — read verified findings + relationships and propose new edges and new leads. Read-only; conservative grading.
- License
- MIT
- Instructions
- 16 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# synthesize Read-only over the run's VERIFIED findings + `dossier/relationships.yaml` + entity records. Do not fetch or edit. 1. **New nodes + edges.** Propose **person nodes** (`dossier/people/<id>.md`) for named individuals surfaced across the findings, plus edges — shared address/phone/email/ officer/director/domain/infra — between entities AND people (person↔entity, person↔person, entity↔entity). Per edge: from-id, to-id, type, confidence (A/B/C/D), supporting source ids. 2. **New leads.** Per lead: target (or null), concrete question, type (registry/infra/corroboration/osint/social), priority 1–5, one-line rationale. 3. Be conservative — only what the verified evidence supports; weak inferences are C/D. Return both lists for the coordinator to merge (leads are for the NEXT run).
From abedegno/needle-osint-agent, MIT.
More from abedegno/needle-osint-agent
- 0.529score
osint-investigation
abedegno
Use when investigating companies, people, or a corporate web from documents and open sources - enforces a sourced, archived, confidence-graded OSINT…
SkillBFreshness: BClaude Code +9 - 0.521score
evaluate-run
abedegno
The run-evaluator's procedure — compute metrics, judge reasoning/missing-tools, write the eval report, open an eval PR.
SkillBFreshness: BClaude Code +9 - 0.521score
research-lead
abedegno
Researcher procedure — discover sources with SearXNG, fetch and snapshot them (text via crawl4ai MCP, screenshots/PDF via shell), extract PDF text, and return…
SkillBFreshness: BClaude Code +9 - 0.521score
run-investigation
abedegno
The coordinator's per-run procedure — drain the open lead queue by dispatching researcher then verifier per lead, record graded findings, run the analyst for…
SkillBFreshness: BClaude Code +9 - 0.521score
verify-finding
abedegno
Verifier procedure — SIFT each finding, try to refute it, require an independent second source (text via crawl4ai MCP, screenshots/PDF via shell), and assign…
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Aug 16, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/abedegno/needle-osint-agent
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from abedegno
- 0.529score
osint-investigation
abedegno
Use when investigating companies, people, or a corporate web from documents and open sources - enforces a sourced, archived, confidence-graded OSINT…
SkillBFreshness: BClaude Code +9 - 0.521score
evaluate-run
abedegno
The run-evaluator's procedure — compute metrics, judge reasoning/missing-tools, write the eval report, open an eval PR.
SkillBFreshness: BClaude Code +9 - 0.521score
research-lead
abedegno
Researcher procedure — discover sources with SearXNG, fetch and snapshot them (text via crawl4ai MCP, screenshots/PDF via shell), extract PDF text, and return…
SkillBFreshness: BClaude Code +9 - 0.521score
run-investigation
abedegno
The coordinator's per-run procedure — drain the open lead queue by dispatching researcher then verifier per lead, record graded findings, run the analyst for…
SkillBFreshness: BClaude Code +9 - 0.521score
verify-finding
abedegno
Verifier procedure — SIFT each finding, try to refute it, require an independent second source (text via crawl4ai MCP, screenshots/PDF via shell), and assign…
SkillBFreshness: BClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get synthesize running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
synthesize skill. Agent Mart. https://agentmart.dev/skills/abedegno-synthesize (last updated 2026-10-24)