agentleFS
fatih-developerfatih-developer/fth-skills/skills/parallel-planner/SKILL.md

parallel-planner

Skill7 starsChanged 42 days agoMITView on GitHub

Analyze multi-step tasks to identify which steps can run in parallel, build dependency graphs, detect conflicts (write-write, read-write, resource contention), and produce optimized execution plans. Triggers on 3+ independent steps, 'speed up', 'run simultaneously', 'parallelize', 'optimize' or any task where sequential execution wastes time.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 8 are distinctive, and 0 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈8

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 0

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Distinctive:

    Not dependent on another step's output

    line 17
  2. Distinctive:

    Does not write to a resource another step reads (no write conflict)

    line 18
  3. Distinctive:

    Does not modify shared state (global variable, same file)

    line 19
  4. Distinctive:

    If it fails, it does not block other parallel steps

    line 20
  5. Distinctive:

    Must be atomic (inside a transaction)

    line 26
  6. Distinctive:

    After identifying parallel candidates, check for conflicts:

    line 44
  7. Distinctive:

    When the steps come from an ecosystem workflow, steps that share a *parallel group* in that workflow are already known to be independent.

    line 62
  8. Distinctive:

    All steps are sequentially dependent

    line 130

≈ “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

Parallel Planner Protocol

Analyze task steps — which ones must wait for each other, which ones can run simultaneously? Build a dependency graph, form parallel groups, and prevent conflicts.

Core principle: Sequential is safe but slow. Parallel is fast but requires care. Making the right distinction is this skill's job.


Parallelization Criteria

A step can run in parallel only if all conditions are met:

  • Not dependent on another step's output
  • Does not write to a resource another step reads (no write conflict)
  • Does not modify shared state (global variable, same file)
  • If it fails, it does not block other parallel steps

A step must run sequentially if any of these apply:

  • Its input is another step's output
  • It writes to the same file / DB table / API resource
  • Order matters for correctness (e.g., schema before data)
  • Must be atomic (inside a transaction)

Parallelizable Work Types

TypeParallel WhenSequential When
Web searchDifferent topics/sourcesResult of search A needed for search B
Code generationWriting to different filesFile B imports from file A
API callsReading from same or different resourcesAuth token needed first
Data processingDifferent data slicesNormalization before analysis
Independent subtasksNo shared output/resourceTest depends on module

Conflict Detection

After identifying parallel candidates, check for conflicts:

Write-Write Conflict

Two steps write to the same resource → cannot be parallel. Solution: Run sequentially OR write to separate files, then merge.

Read-Write Conflict

One step reads while another writes to the same resource → cannot be parallel. Solution: Read first, then write (sequential).

Resource Contention

Shared rate limits or connection pools → limit parallel count. Solution: Cap at 3 parallel, run in batches.


Ecosystem Index

When the steps come from an ecosystem workflow, steps that share a parallel group in that workflow are already known to be independent; start from those groups instead of re-deriving them.

<!-- BEGIN GENERATED: ecosystem-index (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->
EcosystemDomainUse forWorkflows
@ecosystem-orchestrationAgent OrchestrationPlan, execute, recover, remember, and review multi-step agent work; connect external agents safely.orch-complex-task, orch-code-change, orch-resilience, orch-agent-connectivity, orch-knowledge
@ecosystem-reasoningReasoning, Planning Gates & PromptingClarify intent, stress-test plans, compare perspectives, and craft prompts, without stacking redundant question gates.reason-clarify, reason-decision, reason-plan-review, reason-prompting
@ecosystem-apiAPI DomainDesign, secure, scale, and evolve REST, GraphQL, gRPC, and event-driven APIs with a contract-first workflow.api-design, api-security-scale, api-evolution, api-production-readiness
@ecosystem-databaseDatabase DomainModel, secure, optimize, migrate, and operate SQL databases (PostgreSQL, MySQL, SQLite) with data integrity first.db-new-schema, db-performance, db-evolution, db-compliance, db-scaling
@ecosystem-mobileMobile App DomainArchitect, audit, release, and monitor iOS, Android, React Native, and Flutter apps.mobile-pre-release-audit, mobile-release, mobile-feature-architecture, mobile-post-launch
@ecosystem-webWeb, Design & DeliveryDesign product-grade web interfaces, keep design systems consistent, make sites visible to search and AI answer engines, and deploy them.web-foundations, web-build-page, web-visibility, web-review, web-de-slop, web-deploy
@ecosystem-productProduct & GrowthTake a product from focus to market: B2B go-to-market, naming, creative content, and discoverability.product-launch, product-naming, product-content
@ecosystem-securitySecurityAudit skills before deployment, guard agent runtimes against injection and exfiltration, and learn from incidents.sec-skill-audit, sec-runtime-guard, sec-full-lifecycle

Pick the ecosystem whose domain matches the request and follow its workflow map. If the ecosystem skill is not installed, use the workflow ids above as the plan skeleton and run each member skill directly, or install it with npx skills add fatih-developer/fth-skills --skill <ecosystem> after the user agrees. Never invent skills that are not listed.

<!-- END GENERATED: ecosystem-index -->

Output Format

PARALLEL PLANNER
Total steps: N | Parallel groups: N | Sequential steps: N
Estimated speedup: ~X% faster

## Dependency Graph
[mermaid or text visualization]

## Execution Plan

### Group 1 — Parallel (N steps)
- [ ] #A: [step]
- [ ] #B: [step]
- [ ] #C: [step]
-> All complete, then proceed to Group 2

### Group 2 — Sequential
- [ ] #D: [step]  (requires: #A, #B)
- [ ] #E: [step]  (requires: #D)

## Conflict Warnings
[If any — blocked parallel candidates and reason]

## Steps Kept Sequential
| Step | Reason | Depends On |
|------|--------|------------|
| #D | Uses #A output | #A |

Speed Estimate

Sequential total = Sum(all step durations)
Parallel total   = Sum(longest step per group)
Speedup          = (Sequential - Parallel) / Sequential * 100

Complexity-based estimates when duration is unknown:

  • Simple (file read, short code): ~1 unit
  • Medium (API call, analysis): ~3 units
  • Heavy (web research, large code): ~5 units

When to Skip

  • 2 or fewer steps — parallelization is meaningless
  • All steps are sequentially dependent
  • User said "do it step by step"
  • Transaction-bound operations (must be atomic)

Guardrails

  • Never parallelize write operations to the same resource — even if it seems safe.
  • Always show the dependency graph — the user must see why steps are ordered this way.
  • Cross-skill: works with task-decomposer (provides the step list) and tool-selector (optimizes tool usage within groups).

References

  • references/EXAMPLES.md — dependency graphs and parallel execution plans for real tasks. Read it when the expected output format or level of detail is unclear.

🔗 Next Steps & Handoffs

<!-- BEGIN GENERATED: handoffs (generated from the ecosystem workflow map by build_ecosystems.py — do not edit by hand) -->

Ecosystem: @ecosystem-orchestration — Agent Orchestration.

Workflows:

  • Complex Task Execution Flow (orch-complex-task, step 2 of 6): next → @tool-selector (optional).

Handoff contract: pass results to the next skill through an inline Handoff block in your reply with the fields skill, workflow, created_at, inputs, summary, and next (the handoff contract of @ecosystem-orchestration). If a next skill is not installed, continue with its step from the ecosystem map, or install it with npx skills add fatih-developer/fth-skills --skill <name> after the user agrees.

<!-- END GENERATED: handoffs -->

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.