Ready to supercharge your AI agents?

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

AI Prompting Patterns & Agent Communication · jamestorrevillas | DecimalAI

agent toolingby jamestorrevillas

AI Prompting Patterns & Agent Communication

jamestorrevillas/ai-prompting-patterns

Source jamestorrevillas/dev-skills ↗License MIT

Use this skill when designing how an AI agent should communicate with developers — intent clarification, progress reporting, ambiguity handling, confirmation before irreversible actions, error communication, self-correction, task tracking, and plan mode. Also use when building agent UX or defining agent behavior rules. Trigger on keywords: agent communication, intent clarification, plan mode, agent behavior, task tracking, confirmation, agent UX, agentic workflow, agent protocol.

SkillScore86Maintained

Automatic

AI Engineer pack

Last verified 8/3/2026

What it changes

Passed 19 of 22 test cases with the skill, and 12 of 22 without it.

Without skill55%

With skill86%

Checks it passed that the model alone missed

The log specifies what went wrong, the root cause, and the applied principle.
The proposed structure names tasks.md, session.md, and lessons.md for tracking state.
The output pauses and explicitly requests user confirmation before pushing to `main`.

and 7 more in the full report

8 fixed11 passed either way2 still failing1 broke

Pass-rate lift: +32 pp
Tokens: +92%
Agent turns: 0%
Response time: -40%

Model gemini-3.6-flashMeasured 8/3/2026v119 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/jamestorrevillas-ai-prompting-patterns/SKILL.md https://app.decimal.ai/s/jamestorrevillas-ai-prompting-patterns/SKILL.md

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

decimalai skills add jamestorrevillas-ai-prompting-patterns

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

curl -fsSL --create-dirs -o .claude/skills/jamestorrevillas-ai-prompting-patterns/SKILL.md https://app.decimal.ai/s/jamestorrevillas-ai-prompting-patterns/SKILL.md

Raw file: /s/jamestorrevillas-ai-prompting-patterns/SKILL.md ↗ · machine-readable summary at /s/jamestorrevillas-ai-prompting-patterns.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

The developer asks: 'Can you update the README with installation steps?' Provide the immediate response.

What was checked, without and with the skill
Checked	Without skill	With skill
The response omits conversational filler phrases such as 'Certainly!' or 'Great question!'.	Missed	Passed

case-18 · gemini-3.6-flash · 8/3/2026 · answers are capped and redacted

What's inside

The instructions your model reads when the skill loads.

SKILL.md307 linessingle file

AI Prompting Patterns & Agent Communication

Core Principle

An agent that acts confidently on wrong assumptions costs more than an agent that pauses to ask.

The goal is not maximum autonomy — it's maximum useful autonomy. An agent should be autonomous enough to not constantly interrupt, but disciplined enough to catch itself before doing something irreversible or wrong.

The Autonomy Dial

Set the right autonomy level based on task risk:

Level	Mode	When to Use
1	Observe & Suggest	High-risk environment, new agent, first interactions
2	Plan & Propose	Complex tasks — agent creates plan, every step needs approval
3	Act with Confirmation	Agent prepares full action sequence, asks for final go/no-go
4	Act Autonomously	Pre-approved, low-risk, reversible tasks only

Default: Level 2 for complex tasks, Level 3 for well-defined tasks, Level 4 only for formatting/style changes.

Intent Clarification

When to Ask (Ask-when-Needed Protocol)

Ask before acting when:

A key parameter is missing
There are multiple valid interpretations
The task spans multiple files or systems
The action could be hard to reverse
Confidence in understanding is below threshold

Don't ask when:

The task is simple and single-responsibility
Context makes intent obvious
The question can be answered by reading the codebase

Track record

Benchmark

19 / 22

test cases passed, vs 12 / 22 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 — 8/1/2026

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

jamestorrevillas / dev-skills

.github/skills/ai-prompting-patterns/SKILL.md

View on GitHub ↗

License MITImported 8/1/2026Version 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

AI Prompting Patterns & Agent Communication

Core Principle

The Autonomy Dial

Intent Clarification

When to Ask (Ask-when-Needed Protocol)

Track record

Benchmark

Adoption

SkillSafety

Source

Related skills