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

96%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

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.

A well-structured capability skill: actionable commands, clear when/when-not guidance, and clean progressive disclosure to two real reference files. The only friction is mild over-specification of platform storage paths in the main body that could live in the CLI reference.

Suggestions

Move the per-platform storage path detail (`.claude/projects/`, `.codex/sessions/`, Pi settings resolution, `~/.zcode/cli/db/db.sqlite`) from the body into references/cli-quick-reference.md to tighten the overview.

Consider trimming or tabularizing the 'What `trellis mem` is' paragraph so the body leads with the capability and defers platform plumbing to the reference.

Dimension	Reasoning	Score
Conciseness	The body is lean and assumes Claude's competence with no concept-explaining padding; however the 'What `trellis mem` is' paragraph carries platform-specific path detail (`.claude/projects/`, `.codex/sessions/`, Pi settings resolution, ZCode sqlite path) that could be trimmed or moved to the CLI reference. Not a 5 because that operational minutia slightly exceeds what each turn needs.	4 / 5
Actionability	Provides copy-paste-ready commands covering the 80% case (`trellis mem search`, `extract --phase brainstorm`, `context --turns 3 --around 2`, `list --cwd`) with inline comments explaining flags and a clear list→extract fallback when the session id is unknown.	5 / 5
Workflow Clarity	Although framed as a capability skill rather than a fixed workflow, the body sequences the typical flow (search/list → extract/context) and gives explicit decision branches for what to do with results; no destructive steps exist so no validation checkpoint is required, and the simple-skill exception applies.	5 / 5
Progressive Disclosure	SKILL.md is a concise overview with two clearly-signaled, one-level-deep references (`references/cli-quick-reference.md` for full CLI detail, `references/triggering-patterns.md` for verbatim phrasings); both files exist and there is no reference nesting.	5 / 5
	Total	19 / 20 Passed

Description

100%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 description: concrete capabilities, rich bilingual trigger phrases, and explicit what/when guidance with minimal conflict risk. The mild second-person framing ('decide for the moment whether...') is instructional rather than a 'You can use this' pattern, so no voice penalty applies.

Dimension	Reasoning	Score
Specificity	Names the concrete capability ('Reach into past AI conversation history through the `trellis mem` CLI') and enumerates multiple concrete actions — list, search, slice by task boundaries, dump cleaned dialogue — plus disposition options (update spec, append notes, quote inline, internalize), giving comprehensive coverage.	5 / 5
Completeness	Explicitly answers both 'what' (indexes and returns past conversation dialogue via `trellis mem`) and 'when' ('Use whenever the user asks...') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Comprehensive natural trigger coverage in both English and Chinese ('how did we solve X last time', '之前讨论过吗', '想起一段对话') alongside scenario triggers (brainstorm overlap, familiar-bug debugging, cross-session continuation, finish-work review).	5 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (cross-session memory recall via a specific local CLI) and explicitly distinguishes itself from `trellis-update-spec` and the platform task/spec workflow, minimizing conflict risk.	5 / 5
	Total	20 / 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: 64e6636

Reviewed: 5 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.