- Home
- Skills
- Agents & Orchestration
- Causal Timeline Sleuth
More screenshots
Works with the AI Agents you already use
Causal Timeline Sleuth
Reconstruct causal chains, decision timelines, and counterfactual histories from months or years of organizational events.
$15
Causal Timeline Sleuth
Example session with this skill installed
What decisions led us to adopt OAuth2 for authentication?
- Read your context and instructions
- Compiled the causal timeline sleuth
Causal Chain: OAuth2 Adoption (auth-service)
Critical Path
-
2025-03-14 — Credential breach via legacy token endpoint
- Actors: Security team, Platform lead
- Rationale: Legacy tokens had no expiry or rotation
- Evidence: INC-2847 postmortem, security review ticket
- Confidence: high
-
2025-03-21 — Security review mandates token endpoint deprecation within 90 days
- Actors: CISO, Platform lead
- Caused by: 2025-03-14 breach
- Rationale: Compliance + customer trust requirements
- Evidence: SEC-Review-031
- Confidence: high
-
2025-05-08 — OAuth2 selected over SAML after vendor evaluation
- Actors: Platform eng, Security, External consultant
- Caused by: 2025-03-21 mandate
- Rationale: Better library support, existing API gateway already spoke OAuth2, lower migration cost than SAML
- Evidence: ADR-042, evaluation matrix
- Confidence: high
-
2025-06-01 — OAuth2 migration completed, legacy endpoint retired
- Actors: Auth team
- Caused by: 2025-05-08 decision
- Evidence: PR #1842, release notes v2.14
- Confidence: high
Key Branch Points
SAML vs OAuth2 (May 2025): SAML stronger on enterprise SSO features but required heavier gateway changes. OAuth2 won on implementation velocity and existing library maturity.
Why This Path Was Taken
The breach created non-negotiable timeline pressure. Once the 90-day clock started, the team optimized for the solution that could ship inside the window with the least new infrastructure.
Gaps & Confidence Notes
- Exact cost comparison numbers from the May evaluation are not in the current ADR.
- No formal record of the rejected “stay on sessions + add rotation” proposal beyond a single Slack thread.
Sources used: ADR-042, INC-2847, SEC-Review-031, git history of auth-service.
Connects securely to your tools. The creator never sees your data.
About this skill
AI agents fail on temporal-causal questions — not because they lack intelligence, but because they receive the wrong kind of context.
This skill gives your agent the exact architecture patterns, event-graph schema, and query-routing logic needed to answer:
- What decisions led to X?
- How did this situation evolve?
- Why does this system state exist?
- What if we had chosen differently?
What you get
- Clear classification of Sequence / Causal / Counterfactual queries
- A practical Event Graph schema (timestamp, actors, caused_by, confidence, sources)
- Rules for extracting only the causal path from noisy history (ADRs, incidents, git, tickets, meetings)
- Windowed context synthesis so critical intermediate decisions survive context compression
- Structured output formats that are scannable in under 30 seconds
- Explicit confidence scoring and gap reporting — no invented rationales
Ideal for
- Post-incident analysis and root-cause reconstruction
- Architecture Decision Record (ADR) querying across months
- Product retrospectives and strategy evolution
- Compliance / audit “why does this policy exist?” questions
- Organizational memory and institutional knowledge agents
Works with any agent that supports the open SKILL.md standard (Claude Code, Cursor, Codex, Copilot, Gemini CLI, Grok, and 15+ more).
Find more skills like this on the Claude Skills Marketplace, the Codex Skills Marketplace and the Gemini Skills Marketplace, or browse Claude Skills for Agents & Orchestration.
- Requires source material that contains timestamps or clear chronological order (ADRs, incident tickets, git history, meeting notes, changelogs). Purely narrative or undated documents produce weaker chains.
- Does not automatically crawl external systems. The agent must already have access to the relevant files, tickets, or repositories.
- Counterfactual projections are reasoned extrapolations based on the documented baseline, not simulations. Confidence is explicitly marked and can be low when evidence is sparse.
- Very long multi-year histories may need the user to narrow the time window or focus on a specific decision path for best results.
- Does not replace a formal knowledge-graph database. It constructs an in-context event graph; for permanent organizational memory a separate store is still recommended.
How to use
- 1
Connect your agent to the Agensi MCP
Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup
- 2
Sign in to Agensi
Your agent shows a sign-in link. Sign in and click Allow.
- 3
Ask for what you need
Your agent loads this skill and uses it on your task. It always asks before buying a skill.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill goes through the trust checks below.
Security scanned
Checked by our 8-point scan before listing
Fresh listing
Recently published to Agensi
Money-back guarantee
Doesn't do what its page promises? You get your money back.
Trust & safety
Security scan
Security scan passed 2 months ago
Permissions
No special permissions declared or detected