Ready to supercharge your AI agents?

Install any skill in seconds. Free to start, no credit card required.

Session Search · ar9av | DecimalAI

agent toolingby ar9av

Session Search

ar9av/session-search

Source ar9av/obsidian-wiki ↗License MIT

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.

SkillScore36Maintained

Automatic

Knowledge Management pack

Last verified 8/10/2026

What it changes

Passed 4 of 12 test cases with the skill, and 2 of 12 without it.

Without skill14%

With skill36%

Checks it passed that the model alone missed

Passes --json to obsidian-wiki sessions-query.
Explains that the transcript file was pruned from disk.
Filters out transcript lines where isSidechain is true.

and 3 more in the full report

5 fixed3 passed either way14 still failing0 broke

Pass-rate lift: +23 pp
Tokens: +11%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 8/10/2026v18 of 22 cases passed with skill · 12 comparable

Tokens, turns and time describe resource use, not a dollar price.

Use this skill

Save it into your project's skills folder. Claude Code picks it up in its next session.

curl -fsSL --create-dirs -o .claude/skills/ar9av-session-search/SKILL.md https://app.decimal.ai/s/ar9av-session-search/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add ar9av-session-search, and start Claude Code with claude --plugin-dir "$(git rev-parse --show-toplevel)/.agents"

1 · One-time — install the CLI (docs ↗)

pip install "decimalai>=0.15"

2 · Get the skill — writes .agents/skills/ar9av-session-search/ and pins it in .decimal/skills.lock

decimalai skills add ar9av-session-search

No CLI? Get the same file — curl · raw file

curl -fsSL --create-dirs -o .claude/skills/ar9av-session-search/SKILL.md https://app.decimal.ai/s/ar9av-session-search/SKILL.md

Raw file: /s/ar9av-session-search/SKILL.md ↗ · machine-readable summary at /s/ar9av-session-search.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 5 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 5

Prompt

Search past chat sessions for Kubernetes ingress controllers and output the machine-readable JSON structure for script processing.

What was checked, without and with the skill
Checked	Without skill	With skill
Passes --json to obsidian-wiki sessions-query.	Missed	Passed

case-10 · gemini-3.6-flash · 8/10/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md86 linessingle file

Session Search

Answers "which of my past sessions was about X" and then pulls that session's context in.

Step 1: Check the graph exists and is fresh

obsidian-wiki sessions-query "<topic>" --json

If this exits 1 with "run sessions-build first", tell the user and offer /session-brain. If graph.json is more than ~7 days old, mention it and offer a rebuild — but do not silently rebuild, since that is a multi-second operation the user did not ask for.

Step 2: Rank

The scoring already combines four signals, so take the ordering as given rather than re-ranking:

similarity — TF-IDF cosine against the session's text
cluster lift — a session inside the best-matching topic scores higher even if its own words never matched. This is why a session that never said "telemetry" can still surface for it.
bookmark boost — a human already flagged this session as worth keeping
time decay — 90-day half-life, applied with a floor so an old exact match still outranks a fresh weak one

Useful filters: --project NAME, --cluster N, --since DATE, --top N.

Step 3: Present

Show the top ~5 as a compact table — title, project, date, topic, and the why string, which already explains the match. Do not dump the raw JSON at the user.

Two things must be stated honestly rather than glossed over:

Entries with loadable: false are history-only: the transcript has been pruned from disk and only the prompts survive. They are listed in unloadable with a reason. Say the transcript is gone; do not imply it can be retrieved.
If everything relevant is unloadable, answer from the prompt text that is there and say that is all that remains.

Track record

Benchmark

4 / 12

test cases passed, vs 2 / 12 without

Adoption

Users: 0
Times used: 0

Safety and source details

SkillSafety

✓ 3 of 3 passed

Code scan15 of 15 checks clean

0 critical · 0 warning · 0 info — scanner v4 — 8/3/2026

View 15 scanner checks

live_secretremote_code_executionreverse_shelldata_exfiltrationssrf_metadataagent_snoopinganti_refusaldestructive_commandsobfuscated_unicodeunicode_homoglyphopaque_blobsuspicious_urltool_overreachtrigger_abuseprompt_injection_phrasing

IntentSafe

LLM judge · does the skill do what it claims

ContentClean

LLM judge · policy & harmful-content review

Source

Imported

ar9av / obsidian-wiki

.skills/session-search/SKILL.md

View on GitHub ↗

License MITImported 10/8/2026Version v1

More skills from the same source and nearby in the registry, with their headline benchmark lift.

Ready to supercharge your AI agents?

See it in action

What's inside

Session Search

Step 1: Check the graph exists and is fresh

Step 2: Rank

Step 3: Present

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills