d-oitd-oit/rust-2026-template/.agents/skills/goap-agent/SKILL.md

goap-agent

Skill15 starsChanged 5 months agoMITView on GitHub

Invoke for complex multi-step tasks requiring intelligent planning and multi-agent coordination. Use when tasks need decomposition, dependency mapping, parallel/sequential/swarm/iterative execution strategies, or coordination of multiple specialized agents with quality gates. Triggers: "complex task", "plan implementation", "multi-step", "coordinate agents".

1 other project uses a version of this, 1 of them edited.

Adopted by

Most recently taken up by

d-o-hub/github-template-ai-agentsedited, first seen Nov 3, 2026

Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 1
d-o-hub/github-template-ai-agents★ 232% same
Wrote their own version · 0
None found.
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository29 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- llms-full.txtllms.txt
- llms.txtllms.txt
- anti-ai-slopSkill
- architecture-diagramSkill
- atomic-commitSkill
- build-rustSkill
- codacySkill
- crates-io-name-checkSkill
- dora-reportSkill
- harnessSkill
- issue-triageSkill
- lint-rustSkill
- metrics-reporterSkill
- privacy-firstSkill
- release-rustSkill
- reviewing-pull-requestsSkill
- secret-lintSkill
- self-fix-loopSkill
- skill-creatorSkill
- skill-evaluatorSkill
- stacked-prsSkill
- task-decompositionSkill
- test-rustSkill
- tokio-performanceSkill
- triz-analysisSkill
- triz-solverSkill
- verify-actionsSkill

The file

We split this skill into the rules it gives an agent

4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.

≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Always use the plans/ folder for all files.
line 22
Distinctive:
Never paste commit hashes, PR/issue numbers, CI logs, or host-local notes into the pointer file.
line 27
Very specific:
Analyze: Use triz-analysis or triz-solver to evaluate the problem and resolve contradictions.
line 40
Distinctive:
Gate: Wait for human approval of the ADR before proceeding to decomposition.
line 42

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

GOAP Agent Skill: Goal-Oriented Action Planning

Enable intelligent planning and execution of complex multi-step tasks through systematic decomposition, dependency mapping, and coordinated multi-agent execution.

Always use the plans/ folder for all files. Use plans/GOAP_STATE.md to track persistent state.

GOAP_STATE.md is a tracked pointer file (at most 20 lines: goal, active-plan pointer, last-verified stamp, next steps) — see ADR 0005. Per-task detail lives in plans/<nn>-<slug>.md and is indexed by plans/_status.json:active_plan. Never paste commit hashes, PR/issue numbers, CI logs, or host-local notes into the pointer file; update it on handover only.

Core GOAP Methodology

The GOAP Planning Cycle

1. ANALYZE → 2. DECOMPOSE → 3. STRATEGIZE → 4. COORDINATE → 5. EXECUTE → 6. SYNTHESIZE

Phase 1: Task Analysis

Analyze: Use triz-analysis or triz-solver to evaluate the problem and resolve contradictions.
Decide: Formulate an ADR (Architecture Decision Record) in plans/adr/.
Gate: Wait for human approval of the ADR before proceeding to decomposition.

## Task Analysis

**Primary Goal**: [Clear statement of what success looks like]
**Constraints**: [Time, Resources]
**Complexity**: Simple/Medium/Complex
**ADR Link**: [Link to approved Architecture Decision Record]

Phase 2: Task Decomposition

Use task-decomposition skill:

### Sub-Goals
1. [Component 1] - Priority: P0, Deps: none
2. [Component 2] - Priority: P1, Deps: Component 1

Principles: Atomic, Testable, Independent, Assigned

Phase 3: Strategy Selection

Strategy	When	Speed
Parallel	Independent tasks	Nx
Sequential	Dependent tasks	1x
Swarm	Many similar tasks	~Nx
Hybrid	Mixed requirements	2-4x

Phase 4: Agent Assignment

Agent	Best For
feature-implementer	New functionality
debugger	Bug fixes
test-runner	Test validation
refactorer	Code improvements
code-reviewer	Quality assurance

Phase 5: Coordinated Execution

Parallel: Single message, multiple Task tool calls Sequential: Phases with quality gates between Monitor: Track progress, validate results

Phase 6: Result Synthesis

## Summary

✓ Completed: [Tasks]
📦 Deliverables: [List]
✅ Quality: [Status]

Common Patterns

Research → Implement → Validate
Investigate → Diagnose → Fix → Verify
Audit → Improve → Validate

Rationalizations

Rationalization	Reality
"I can just execute all tasks in parallel — it's faster."	Parallel execution without dependency analysis causes race conditions and wasted tokens.
"Quality gates slow things down — skip them for speed."	Skipping quality gates compounds errors across agents, requiring far more rework.

Red Flags

Executing tasks without mapping dependencies first
Skipping ADR approval gate before decomposition
Assigning agents without matching skills to task requirements

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

It worked
Partly
It didn't

What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free