coding-agent-sessions

Finds, reads, and reconstructs coding-agent sessions across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs. Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did.

Quality

94%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Quality

Content

92%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-structured operational guide: fully executable commands, a clearly sequenced workflow with an explicit verification step, and clean one-level-deep progressive disclosure into real reference files. The only weakness is mild bulk in the output-field and troubleshooting tables that could be tightened or offloaded to a reference file.

Dimension	Reasoning	Score
Conciseness	The body is dense and nearly every token is novel operational fact (store locations, flags, linkage tables, filter semantics), but the 16-row Output Contract field table and lengthy troubleshooting rows (e.g., the Aside entry) carry detail that could be trimmed or moved. This matches the score-4 anchor (efficient, minor instances that could be trimmed) rather than 5 (lean) or 3, since nothing explains concepts Claude already knows and no section is padded.	4 / 5
Actionability	Every section gives copy-paste-ready commands (e.g., `find "commit" --from 7d --platform senpi --platform opencode`) plus exact flag/filter tables, exact store paths, and ready-to-run `detail_hint` commands. There are no gaps — commands are executable as written and the multi-query/subagent examples cover typical usage — so it exceeds the score-4 anchor.	5 / 5
Workflow Clarity	Phase 0 gives a clearly numbered sequence: platform router first, broad finder with query-lane expansion, parallel explorer lanes, read via detail_hint, then explicit verification ("Verify by opening raw transcripts for claims"), with the Troubleshooting table serving as the error-recovery loop. No destructive or batch operations are involved, so the validation cap does not apply, and the explicit verification checkpoint matches the score-5 anchor.	5 / 5
Progressive Disclosure	SKILL.md is a genuine overview with per-platform detail split one level deep into five real reference files (references/codex.md, claude.md, senpi.md, opencode.md, all-platforms.md — all present in the bundle), clearly signaled by the platform-router table, plus a real scripts/find-agent-sessions.py. References are well signaled, one level deep, verified to exist, and the split is exactly appropriate, so it exceeds the score-4 anchor.	5 / 5
	Total	19 / 20 Passed

Description

92%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: concrete multi-action capability statement, explicit platform enumeration, and a clear "Use when" trigger clause covering natural user phrasings. The only minor gap is absence of a few common synonyms such as "chat history" or "conversation logs".

Dimension	Reasoning	Score
Specificity	"Finds, reads, and reconstructs" names three concrete actions and enumerates the specific platforms covered ("across Codex, Claude, OpenCode, OMO/Senpi, and other local agent logs"), matching the comprehensive multi-action anchor rather than the score-4 anchor with minor gaps.	5 / 5
Completeness	It explicitly answers what ("Finds, reads, and reconstructs coding-agent sessions") and when ("Use when asked to find or search past sessions, transcripts, or subagent runs, or to recover what an earlier session did") with concrete trigger phrases, matching the score-5 anchor exactly.	5 / 5
Trigger Term Quality	"find or search past sessions, transcripts, or subagent runs" and "recover what an earlier session did" are natural user phrasings with good coverage, but common synonyms like "chat history", "conversation logs", or "past chats" are missing, so it sits just below the comprehensive synonym coverage of the score-5 anchor.	4 / 5
Distinctiveness Conflict Risk	The niche is clear (local coding-agent session/transcript recovery) with distinct triggers unlikely to fire for unrelated skills; not the score-4 anchor since no meaningful overlap with closely related skills is apparent.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: code-yeongyu/lazycodex
Path: plugins/omo/skills/coding-agent-sessions/SKILL.md
Commit: 9f97b58

Reviewed: 8 days 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.