building-incident-timeline-with-timesketch

Build collaborative forensic incident timelines using Timesketch to ingest, normalize, and analyze multi-source event data (including Plaso output) for attack chain reconstruction and investigation documentation. Use when reconstructing the sequence of events during an incident investigation or when multiple analysts need to jointly tag, annotate, and search a shared DFIR timeline.

Quality

82%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

High

Do not use without reviewing

Quality

Content

65%

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is highly actionable with executable commands, queries, and code, and is reasonably well-sectioned. Its main weaknesses are templated/overview padding that hurts conciseness, missing validation checkpoints in the ingestion workflow, and orphaned bundle files that the body never navigates to.

Suggestions

Replace the generic "When to Use" boilerplate and trim the Overview's tool-description prose so every remaining line is instruction, not background Claude already knows.

Add explicit verification checkpoints to the ingestion/analysis workflow (e.g., confirm indexing completed and verify event counts per timeline before running analyzers), turning it into a validate-then-proceed loop.

Link the existing bundle files from the body — point to references/workflows.md for the evidence-processing pipelines, references/api-reference.md for endpoint details, references/standards.md for frameworks, and assets/template.md for the report template — and move the inlined API/workflow/standards content into those files.

Dimension	Reasoning	Score
Conciseness	Mostly efficient with concrete commands, queries, and tables, but the Overview paragraph explains what Timesketch is ("open-source collaborative forensic timeline analysis tool developed by Google") and the "When to Use" section is generic templated boilerplate ("When deploying or configuring building incident timeline with timesketch capabilities in your environment"). Not a 3 because these passages do not earn their tokens; not a 1 because the bulk is actionable rather than padded concept explanation.	2 / 3
Actionability	Provides copy-paste-ready, executable guidance throughout: docker compose commands, log2timeline.py parser invocations, timesketch_importer calls, CSV/JSONL schemas, Timesketch query-language examples, a Python API client snippet, and a Dissect target-query example.	3 / 3
Workflow Clarity	The Analysis Workflow lays out a clear Step 1–4 sequence, but it contains no validation or verification checkpoints for the batch ingestion/indexing operations, so per the rubric workflow_clarity is capped at 2. Not a 1 because the steps are clearly ordered rather than missing; not a 3 because there are no feedback loops (e.g., verify indexing complete, verify event counts).	2 / 3
Progressive Disclosure	Bundle files exist (references/api-reference.md, references/standards.md, references/workflows.md, assets/template.md, scripts/agent.py, scripts/process.py) but the body never links or signals them — its "References" section lists only external URLs — while content that belongs in those bundles (API automation code, workflows, standards) is inlined. Fits the score-2 anchor (structure present, references not signaled, content that should be separate is inline). Not a 1 because the body is well-sectioned rather than a monolithic wall, and not a 3 because the one-level-deep references are absent.	2 / 3
	Total	9 / 12 Passed

Description

100%

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, third-person description that names concrete capabilities, supplies explicit "Use when" triggers, and occupies a distinct niche with minimal conflict risk. It is concise without padding and avoids over-claims.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions — "ingest, normalize, and analyze multi-source event data", "attack chain reconstruction", "investigation documentation", and "tag, annotate, and search" — matching the multi-action anchor.	3 / 3
Completeness	Explicitly states what it does (build/ingest/normalize/analyze timelines) and gives an explicit "Use when reconstructing the sequence of events... or when multiple analysts need to jointly tag, annotate, and search a shared DFIR timeline" trigger, satisfying both what and when.	3 / 3
Trigger Term Quality	Uses natural terms a user would say during an incident ("incident timeline", "incident investigation", "tag, annotate, and search", "DFIR timeline", "attack chain reconstruction"); domain terms like DFIR/Plaso are natural here, not alienating jargon.	3 / 3
Distinctiveness Conflict Risk	Targets a clear niche (collaborative Timesketch DFIR timeline building) with distinct triggers; unlikely to fire for unrelated skills. Not scored 2 because it is not merely "somewhat specific" — the Timesketch/collaborative-multi-analyst framing is sharply scoped.	3 / 3
	Total	12 / 12 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: mukul975/Anthropic-Cybersecurity-Skills
Path: skills/building-incident-timeline-with-timesketch/SKILL.md
Commit: e612f49

Reviewed: about 1 hour ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.