CtrlK
BlogDocsLog inGet started
Tessl Logo

session-search

Find a past agent session by topic and load its context into the current conversation. Searches the session-brain topic graph, ranking by relevance, topic membership, and time decay, then loads the winning transcript. Use when the user says "/wiki-sessions <topic>", "which session did I do X in", "find the session where I fixed X", "when did I last work on Y", "what was that session about Z", "load the session where I set up X", "have I done this before". Read-only — never writes to the vault. Requires a graph built by the session-brain skill.

76

Quality

95%

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

96%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.

An efficient, highly actionable read-only search skill with a clearly sequenced workflow and multiple guard checks. Structure is clean and self-contained; the only dimension short of full marks is progressive disclosure, held at 4 by length rather than by any organization defect.

DimensionReasoningScore

Conciseness

Lean and assumes Claude's competence — references 'TF-IDF cosine' and '90-day half-life' without explaining them, and every aside earns its place ('Never read one whole.' directly justifies the filter snippet).

5 / 5

Actionability

Fully executable, copy-paste-ready guidance throughout — 'obsidian-wiki sessions-query "<topic>" --json', named filters '--project NAME --cluster N --since DATE --top N', 'sessions-show <session-id> --pretty', and a complete python JSONL-filter snippet.

5 / 5

Workflow Clarity

A clear 5-step sequence (Check → Rank → Present → Load → Answer) with explicit checkpoints — graph-freshness/exit-1 handling, 'loadable: false'/'unloadable' honesty, and a 'grep -c' size guard before reading the transcript — plus feedback (offer /session-brain).

5 / 5

Progressive Disclosure

Well-organized into Steps 1–5 plus a Related section with one-level-deep links to sibling skills, and no bundle files exist to misroute; at ~90 lines it exceeds the under-50-line simple-skill exception, so it sits just below the 5 anchor.

4 / 5

Total

19

/

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, well-scoped description that pairs a concrete capability summary with an explicit, trigger-rich 'Use when' clause and clear boundary statements. The only soft spot is that the present/filter action is implied rather than stated in the description itself.

DimensionReasoningScore

Specificity

Names the domain plus several concrete actions — 'Searches the session-brain topic graph, ranking by relevance, topic membership, and time decay, then loads the winning transcript' — but the present/filter step is only implied here, leaving minor coverage gaps versus the 5 anchor.

4 / 5

Completeness

Explicitly answers both 'what' (search/rank/load transcript) and 'when' via a concrete 'Use when the user says ...' clause with multiple trigger phrases, matching the 5 anchor.

5 / 5

Trigger Term Quality

Comprehensive natural trigger phrasings with synonyms — 'which session did I do X in', 'find the session where I fixed X', 'when did I last work on Y', 'what was that session about Z', 'have I done this before', '/wiki-sessions <topic>' — exactly what a user would say.

5 / 5

Distinctiveness Conflict Risk

Clear niche actively disambiguated from siblings — 'Read-only — never writes to the vault. Requires a graph built by the session-brain skill' — with distinct session-recall triggers and 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.