trellis-session-insight

Reach into past AI conversation history through the `trellis mem` CLI. Use whenever the user asks 'how did we solve X last time', 'have we discussed this before', 'what was the decision on X', 'remind me what we did in this task', '上次怎么解的', '之前讨论过吗', '想起一段对话', or when starting a brainstorm that overlaps prior work, debugging a familiar bug, continuing a task across sessions, or doing a finish-work review. Returns raw past dialogue; decide for the moment whether to update spec, append to task notes, quote inline in the answer, or just internalize.

Quality

90%

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

86%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.

A well-structured capability skill body that provides executable CLI commands, a clear when/when-not/results decision tree, and properly offloads detailed reference material to bundled files. It assumes Claude's intelligence and avoids padding.

Suggestions

Consider moving the per-platform session-path enumeration (Claude/Codex/Devin/Grok/OpenCode/Pi/ZCode paths) into references/cli-quick-reference.md to further slim the overview body.

Add a brief explicit checkpoint after retrieval (e.g., 'confirm the session-id/phase matches the user's intent before quoting') to make the workflow's implicit checkpoints explicit.

Dimension	Reasoning	Score
Conciseness	Lean and efficient, assumes Claude's competence without explaining basic concepts; the dense enumeration of per-platform session paths is load-bearing but could be tightened slightly.	4 / 5
Actionability	Provides fully executable, copy-paste-ready CLI commands with concrete flags (search, extract --phase, extract --grep, context --turns, list, projects) covering the common cases.	5 / 5
Workflow Clarity	Clear sequencing from discovery (list/projects) to retrieval (search/extract/context) to a decision tree for handling results; no destructive/batch validation needed since mem is explicitly read-only, but checkpoints are implicit rather than explicit.	4 / 5
Progressive Disclosure	SKILL.md is a concise overview with clearly signaled, one-level-deep references to real files (references/cli-quick-reference.md, references/triggering-patterns.md); bulk detail is appropriately split out.	5 / 5
	Total	18 / 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.

A strong, specific description with concrete trigger phrasings in both English and Chinese and an explicit 'Use whenever' clause. It clearly answers both what the skill does and when to reach for it, with minimal conflict risk.

Dimension	Reasoning	Score
Specificity	Names the domain ('past AI conversation history') and several concrete actions via the trellis mem CLI (list, search, extract, context, slice by task boundaries), but the action list is somewhat implied rather than comprehensively enumerated.	4 / 5
Completeness	Explicitly answers both what ('Reach into past AI conversation history through the trellis mem CLI... Returns raw past dialogue') and when ('Use whenever the user asks...'), with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural verbatim phrasings in English ('how did we solve X last time', 'have we discussed this before', 'what was the decision on X') plus bilingual synonyms ('上次怎么解的', '之前讨论过吗', '想起一段对话') that users would actually say.	5 / 5
Distinctiveness Conflict Risk	Clear niche — cross-session past-conversation recall via a specific CLI — with distinct triggers that are unlikely to fire for the wrong skill.	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: mindfold-ai/Trellis
Path: .agents/skills/trellis-session-insight/SKILL.md
Commit: e77ae89

Reviewed: 6 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.