Ready to supercharge your AI agents?

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

Dig Deeper · athola | DecimalAI

researchby athola

Dig Deeper

athola/dig

Source athola/claude-night-market ↗License MIT

Refines an active research session by drilling deeper into a subtopic. Use after tome:research to narrow results to a specific channel or angle.

SkillScore78Maintained

Automatic

Research pack

Last verified 8/28/2026

What it changes

Passed 14 of 18 test cases with the skill, and 5 of 18 without it.

Without skill26%

With skill78%

Checks it passed that the model alone missed

Dispatches search queries restricted to the news channel.
Halts execution without running searches when no session exists.
Lists academic papers and press releases as the available channels.

and 17 more in the full report

13 fixed5 passed either way4 still failing1 broke

Pass-rate lift: +52 pp
Tokens: -28%
Agent turns: 0%
Response time: -16%

Model gemini-3.6-flashMeasured 8/28/2026v218 of 23 cases passed with skill · 18 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/athola-dig/SKILL.md https://app.decimal.ai/s/athola-dig/SKILL.md

Want it pinned and updatable? pip install "decimalai>=0.15", then decimalai skills add athola-dig, 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/athola-dig/ and pins it in .decimal/skills.lock

decimalai skills add athola-dig

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

curl -fsSL --create-dirs -o .claude/skills/athola-dig/SKILL.md https://app.decimal.ai/s/athola-dig/SKILL.md

Raw file: /s/athola-dig/SKILL.md ↗ · machine-readable summary at /s/athola-dig.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 11 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 11

Prompt

Can we expand on the clinical trials aspect from our active oncology research session? Dive further into that specific subtopic and present the updated insights after refreshing our session record.

What was checked, without and with the skill
Checked	Without skill	With skill
Retrieves the active oncology session via SessionManager before dispatching search agents.	Missed	Passed
Displays the new findings to the user only after the session report has been saved.	Missed	Passed

case-03 · gemini-3.6-flash · 8/28/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md43 linessingle file

Dig Deeper

When To Use

Drilling into a subtopic after an initial research session
Narrowing results to a specific channel (e.g. papers only)

When NOT To Use

Starting a new research topic (use /tome:research first)
Synthesizing results (use Skill(tome:synthesize))

Refine an active research session interactively.

Workflow

Load most recent session via SessionManager
Parse the subtopic and optional channel filter
Dispatch targeted search (single agent or all channels)
Merge new findings into existing session
Re-rank and update the saved report
Present new findings to user

Error Cases

No active session: "Start a session first with /tome:research \"topic\""
Specified channel not in original session: warn and suggest available channels

Exit Criteria

Active session loaded from SessionManager before any search executes; if absent, error "Start a session first with /tome:research \"<topic>\"" is emitted and skill halts
New findings merged into the existing session without overwriting prior findings from other channels
Session report re-ranked and saved after the merge so the updated file reflects the deeper search results
If the specified channel is not in the original session,

Track record

Benchmark

14 / 18

test cases passed, vs 5 / 18 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 v5 — 8/26/2026

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

athola / claude-night-market

plugins/tome/skills/dig/SKILL.md

View on GitHub ↗

License MITImported 8/26/2026Version v2

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

Dig Deeper

When To Use

When NOT To Use

Workflow

Error Cases

Exit Criteria

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills