Ready to supercharge your AI agents?

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

Get Started Free →

Dependency Mapping · yogsoth-ai | DecimalAI

researchby yogsoth-ai

Dependency Mapping

yogsoth-ai/dependency-mapping

Source yogsoth-ai/de-anthropocentric-research-engine ↗License Apache-2.0

SOP: map dependency relationships among sub-questions

SkillScore86Maintained

Automatic

Research pack

Last verified 8/22/2026

What it changes

Passed 19 of 22 test cases with the skill, and 14 of 22 without it.

Without skill64%

With skill86%

Checks it passed that the model alone missed

The output states Circular dependencies: NONE.
The output tags SQ1 → SQ3 as a weak dependency.
The output classifies dependency types specifically as strong or weak.

and 5 more in the full report

8 fixed11 passed either way0 still failing3 broke

Pass-rate lift: +23 pp
Tokens: -29%
Agent turns: 0%
Response time: -47%

Model gemini-3.6-flashMeasured 8/22/2026v119 of 22 cases passed with skill

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/yogsoth-ai-dependency-mapping/SKILL.md https://app.decimal.ai/s/yogsoth-ai-dependency-mapping/SKILL.md

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

decimalai skills add yogsoth-ai-dependency-mapping

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

curl -fsSL --create-dirs -o .claude/skills/yogsoth-ai-dependency-mapping/SKILL.md https://app.decimal.ai/s/yogsoth-ai-dependency-mapping/SKILL.md

Raw file: /s/yogsoth-ai-dependency-mapping/SKILL.md ↗ · machine-readable summary at /s/yogsoth-ai-dependency-mapping.json ↗

Safety checks: 3 of 3 passed

Code scan CleanIntent PassedContent Clean

See it in action

One of 8 test cases the skill fixed. Same model, same prompt, with and without the skill.

1 of 8

Prompt

We have three sub-questions for an HR policy update: SQ1: What are the state statutory remote work meal break requirements? SQ2: What is our company's draft remote work policy? SQ3: Does the draft policy in SQ2 align with statutory requirements from SQ1? SQ2 is drafted independently of SQ1, but SQ1 provides helpful background context. Map dependencies with explanations in parenthetical format.

What was checked, without and with the skill
Checked	Without skill	With skill
The output includes a parenthetical note detailing why the weak dependency is non-blocking.	Missed	Passed

case-18 · gemini-3.6-flash · 8/22/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md32 linessingle file

Dependency Mapping

Map dependency relationships among sub-questions — determine which sub-questions must be answered first.

HARD-GATE

Pipeline

Pre-check: is the sub-question list complete
Dependency identification: for each pair of sub-questions, judge whether a dependency exists
Dependency-type tagging: strong dependency (must be completed first) / weak dependency (helpful but not required)
Cycle detection: check whether circular dependencies exist
Critical-path identification: find the longest dependency chain
Parallelization-opportunity identification: find groups of sub-questions that can proceed simultaneously
Output: dependency graph + critical path + parallelization opportunities

Output Format

Dependencies:
  SQ1 → SQ2 (strong: SQ2 needs SQ1's result as input)
  SQ1 → SQ3 (weak: SQ3 benefits from SQ1 but can proceed independently)
  SQ2 → SQ4 (strong)

Circular dependencies: NONE / [list]
Critical path: SQ1 → SQ2 → SQ4 (length: 3)
Parallel groups: [SQ1, SQ3] can run simultaneously

Track record

Benchmark

19 / 22

test cases passed, vs 14 / 22 without

Adoption

Users: 1
Times used: 11

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

yogsoth-ai / de-anthropocentric-research-engine

skills/dependency-mapping/SKILL.md

View on GitHub ↗

License Apache-2.0Imported 8/3/2026Version 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

Dependency Mapping

HARD-GATE

Pipeline

Output Format

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills