CtrlK
BlogDocsLog inGet started
Tessl Logo

codex-history-ingest

Ingest Codex CLI conversation history into the Obsidian wiki. Use this skill when the user wants to mine their past Codex sessions for knowledge, import their ~/.codex folder, extract insights from previous coding sessions, or says things like "process my Codex history", "add my Codex conversations to the wiki", or "what have I discussed in Codex before". Also triggers when the user mentions .codex sessions, rollout files, session_index.jsonl, or Codex transcript logs.

70

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

SKILL.md
Quality
Evals
Security

Quality

Content

75%Weight 40%Scale 1-5

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

The body is a well-sequenced, actionable ingestion workflow with concrete paths, templates, and commands, and it correctly offloads field-level parsing to a real reference file. The main gaps are duplicated privacy guidance, lack of a worked parsing example, and no explicit validation loop on the wiki writes themselves.

Suggestions

Consolidate the privacy guidance into one section to remove the duplication between Step 3's 'Critical privacy filter' and the 'Privacy and Compliance' block.

Add a short worked example showing one rollout JSONL line distilled into a wiki page snippet so the core parsing step is concrete rather than rule-only.

Add an explicit verify-after-write checkpoint (e.g., re-read each created/updated page to confirm frontmatter and provenance) to close the batch-write validation loop.

DimensionReasoningScore

Conciseness

Mostly efficient bullet/code structure that assumes Claude's competence (no explaining of Obsidian or JSONL), but privacy guidance is duplicated between the Step 3 'Critical privacy filter' and the standalone 'Privacy and Compliance' section, and the QMD refresh block is somewhat verbose — minor trim opportunities.

4 / 5

Actionability

Concrete paths, JSON envelope shapes, frontmatter templates, and copy-paste qmd commands give mostly executable guidance, but the core rollout-parsing step provides extraction rules and structure rather than a worked input-to-output example or script, leaving a minor gap.

4 / 5

Workflow Clarity

A clearly numbered six-step sequence with checkpoints (Step 1 delta report before deep parsing, manifest-based append safety, QMD verify) covers a batch operation, but the wiki-write flow itself lacks an explicit validate-then-fix feedback loop, so it sits just below the top anchor.

4 / 5

Progressive Disclosure

Good structure with a real one-level-deep reference (`references/codex-data-format.md`, verified to exist) signaled in a Reference section, but the body still inlines a data-layout tree and JSON envelope that overlap with that reference, a minor organization gap.

4 / 5

Total

16

/

20

Passed

Description

95%Weight 40%Scale 1-5

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

The description is strong: it states a concrete capability, gives explicit 'use when' triggers with both natural phrasings and technical file markers, and carves out a distinct Codex-only niche. Its only weakness is that the listed actions overlap rather than enumerating distinct capabilities.

DimensionReasoningScore

Specificity

Names the domain and several concrete actions ('Ingest Codex CLI conversation history', 'mine their past Codex sessions for knowledge', 'import their ~/.codex folder', 'extract insights') but they describe one ingestion workflow from a few angles rather than four distinct capabilities, leaving minor coverage gaps.

4 / 5

Completeness

Explicitly answers both 'what' (ingest Codex CLI conversation history into the Obsidian wiki) and 'when' ('Use this skill when the user wants to...', 'Also triggers when the user mentions...') with concrete trigger phrases.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrases ('process my Codex history', 'add my Codex conversations to the wiki', 'what have I discussed in Codex before') plus technical synonyms and file/path markers (`.codex sessions`, `rollout files`, `session_index.jsonl`, `~/.codex`), matching the top anchor.

5 / 5

Distinctiveness Conflict Risk

Clear Codex-specific niche with distinct triggers (Codex CLI, `.codex`, rollout files, `session_index.jsonl`) that are unlikely to fire for sibling history-ingest skills, giving minimal conflict risk.

5 / 5

Total

19

/

20

Passed

Validation

100%

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

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
Ar9av/obsidian-wiki
Reviewed

Table of Contents

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.