CtrlK
BlogDocsLog inGet started
Tessl Logo

coding-agent-sessions

MUST USE when asked to find, read, list, search, inspect, fetch, export, or reconstruct coding-agent sessions across Codex, Claude Code/Desktop, OpenCode, Senpi/pi, oh-my-pi (omp), gajae-code (gjc), OpenClaw, Factory Droid, Amp, Gemini/Kimi/Qwen CLIs, Codebuff, Roo/Kilo/Cline, Kodu, Cursor CLI, Aider, or unknown local agent logs. Covers transcripts, session IDs, rollout JSONL, state SQLite, Claude projects/pre-compact histories, OpenCode messages/parts, child/subagent linkage, cwd/model/time/token filters, archives, and cost clues. Expands fuzzy recall into parallel query lanes and first probes known stores so absent platforms are skipped cheaply. Triggers: coding agent sessions, Codex/Claude/OpenCode/Senpi/pi/oh-my-pi/omp/gajae-code/gjc/OpenClaw/Droid/Amp/Kodu/Cursor/Aider sessions, transcript search, session history, session ID, read transcript, token usage, subagent sessions, what did I do yesterday, did we already do this.

80

Quality

100%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

SKILL.md
Quality
Evals
Security

Quality

Content

100%

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

The skill body is a well-structured operational guide: copy-paste executable commands, explicit field/filter reference tables, a sequenced PHASE 0 router with a verification step, and clean one-level-deep references to per-platform detail files. Its only minor weakness is length in the Output Contract and filter tables, but that material is genuinely reference content.

DimensionReasoningScore

Conciseness

The body is dense operational material (executable commands, field/filter tables, troubleshooting fixes) that assumes Claude's competence and avoids explaining what a coding-agent session is; the long field/filter tables are reference data that earns its place rather than padded concept explanation, fitting the lean-and-efficient anchor.

3 / 3

Actionability

Provides fully executable, copy-paste-ready commands (e.g. "python3 scripts/find-agent-sessions.py find --query ... --include-subagents --workers 64") with real flags plus concrete troubleshooting fixes, matching the fully-executable anchor rather than the pseudocode level 2.

3 / 3

Workflow Clarity

PHASE 0 is a numbered, sequenced router (load reference, run finder, expand fuzzy recall, parallel lanes, read details, verify) with an explicit verification step ("Verify by opening raw transcripts for claims") and Activation fallback guidance; it is not the level-2 "steps listed but checkpoints missing" case because verification and re-query recovery are explicit.

3 / 3

Progressive Disclosure

The body is a clear overview router pointing to five real, well-signaled one-level-deep references (references/codex.md, claude.md, senpi.md, opencode.md, all-platforms.md) plus a bundled scripts/ finder, with no nested reference chains, matching the clear-overview-with-one-level-deep-references anchor.

3 / 3

Total

12

/

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.

The description is a strong, explicit trigger-and-capability statement: it names many concrete actions, enumerates platform aliases and storage formats, and provides both a "Use when" clause and a natural-language Triggers list. It risks slight verbosity from the long product enumeration, but every term is discriminative rather than fluff.

DimensionReasoningScore

Specificity

Lists multiple concrete actions ("find, read, list, search, inspect, fetch, export, or reconstruct") plus concrete coverage specifics like "rollout JSONL, state SQLite, child/subagent linkage, cwd/model/time/token filters", matching the multi-action anchor rather than the single-domain level 2.

3 / 3

Completeness

Explicitly answers what (cross-platform coding-agent session finding plus format coverage) and when (a "MUST USE when..." clause plus a dedicated "Triggers:" list), matching the both-answered anchor rather than the when-implied level 2.

3 / 3

Trigger Term Quality

Broad coverage of natural user phrasing ("what did I do yesterday", "did we already do this", "transcript search", "session history", "read transcript", "token usage") plus named product aliases, well beyond the partial level 2 anchor.

3 / 3

Distinctiveness Conflict Risk

The niche is highly specific (reconstructing local coding-agent sessions across named products) with distinct trigger vocabulary unlikely to collide with other skills, matching the clear-niche anchor.

3 / 3

Total

12

/

12

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
code-yeongyu/lazycodex
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.