planning
Skill6 starsChanged 14 days agoMITView on GitHub
Plan broad or risky Nacelle work. Use for architecture changes, migrations, release or production-readiness assessments, security hardening, performance baselines, documentation restructuring, validation strategies, or multi-session work.
69 other projects use a version of this.
Adopted by
Most recently taken up by
- gimso2x/claude-harness-slim-templatetheir own version, first seen Nov 8, 2026
- t128n/skillstheir own version, first seen Nov 8, 2026
- juriwiens/skillstheir own version, first seen Nov 8, 2026
- AlomoesDataScience/claude-skillstheir own version, first seen Nov 8, 2026
- RiccardoGrin/skillstheir own version, first seen Nov 8, 2026
- iliaal/ai-skillstheir own version, first seen Nov 7, 2026
Used with
Projects with it also use Problem-Solving Techniques, executing and 10 more.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
truongtv22SkillProblem-Solving Techniques
Apply systematic problem-solving techniques for complexity spirals (simplification cascades), innovation blocks (collision-zone thinking), recurring patterns (meta-pattern recognition), assumption constraints (inversion exercise), scale uncertainty (scale game), and dispatch when stuck. Techniques derived from Microsoft Amplifier project patterns adapted for immediate application.
Also in 5 projects that use this
LucasDuysSkillexecuting
Autonomous task implementation workflow — implement, test, review, commit for each task in the frontier
Also in 3 projects that use this
mrgoonieSkillweb-frameworks
Build modern full-stack web applications with Next.js (App Router, Server Components, RSC, PPR, SSR, SSG, ISR), Turborepo (monorepo management, task pipelines, remote caching, parallel execution), and RemixIcon (3100+ SVG icons in outlined/filled styles). Use when creating React applications, implementing server-side rendering, setting up monorepos with multiple packages, optimizing build performance and caching strategies, adding icon libraries, managing shared dependencies, or working with TypeScript full-stack projects.
Also in 5 projects that use this
mrgoonieSkillmcp-management
Manage Model Context Protocol (MCP) servers - discover, analyze, and execute tools/prompts/resources from configured MCP servers. Use when working with MCP integrations, need to discover available MCP capabilities, filter MCP tools for specific tasks, execute MCP tools programmatically, access MCP prompts/resources, or implement MCP client functionality. Supports intelligent tool selection, multi-server management, and context-efficient capability discovery.
Also in 5 projects that use this
renathoazSkillverifying
Verify work before claiming done.
Also in 3 projects that use this
truongtv22Skillmobile-development
Build modern mobile applications with React Native, Flutter, Swift/SwiftUI, and Kotlin/Jetpack Compose. Covers mobile-first design principles, performance optimization (battery, memory, network), offline-first architecture, platform-specific guidelines (iOS HIG, Material Design), testing strategies, security best practices, accessibility, app store deployment, and mobile development mindset. Use when building mobile apps, implementing mobile UX patterns, optimizing for mobile constraints, or making native vs cross-platform decisions.
Also in 4 projects that use this
- +6 more from mrgoonie
Other versions69 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 69
- langchain-ai/deepagents★ 31ksame name
- open-metadata/OpenMetadata★ 16ksame name
- atopile/atopile★ 4ksame name
- awslabs/agent-plugins★ 918same name
- xiaolai/vmark★ 908same name
- ryanthedev/code-foundations★ 381same name
- mblode/agent-skills★ 189same name
- markmdev/meridian★ 184same name
- tmcfarlane/team-avatar★ 112same name
- Towow-ai/Flowness★ 107same name
59 more not listed
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 repository5 other files it gives its agents.
- .github/copilot-instructions.mdCopilot instructions
- code-reviewSkill
- docs-reviewSkill
- nacelle-reviewSkill
- pr-descriptionSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 6 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 62 edited versions we read keep these.
6
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Use chat for plans unless the user requests a durable plan file.
- Distinctive: line 16
Keep internal assessments and decisions separate from public operator, API, user, and release documentation.
- Distinctive: line 18
Leave implementation tactics to the owning crate and nearby code unless they affect ordering, risk, validation, compatibility, or …
- Distinctive: line 19
When the user requests only a plan, do not implement or commit changes.
- Distinctive: line 29
Update durable plans as facts change, preserving useful decisions and marking superseded assumptions clearly.
- Very specific: line 54
Do not describe Nacelle as production ready without scope.
- Distinctive: line 59
not yet ready for public or regulated workloads
“Common” is measured: kept by at least 6 in 10 of the 62 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Planning Nacelle Work
Turn substantial goals into scoped, ordered work with explicit risks, validation gates, and handoff-ready checkpoints.
Scope
- Inspect the relevant repository state, architecture documentation, manifests, modules, tests, configuration, scripts, CI, and recent commits before planning.
- Apply the repository's general communication and documentation styles to plans. Preserve required technical evidence and safety details when brevity would obscure them.
- Use chat for plans unless the user requests a durable plan file. For requested broad, risky, architectural, release, migration, or multi-session plans, include enough evidence for a persistent handoff.
- Continue the nearest existing plan when it matches the goal. If no convention exists and a durable plan is justified, use
.github/plans/YYYY-MM-DD-<topic>.md. - Keep internal assessments and decisions separate from public operator, API, user, and release documentation.
- Plan files under
.github/plans/and working documents underdocs/internal/stay ignored and untracked; do not add ignore exceptions. - Leave implementation tactics to the owning crate and nearby code unless they affect ordering, risk, validation, compatibility, or architecture.
- When the user requests only a plan, do not implement or commit changes.
Procedure
- Name the target: feature, bug class, migration, architecture change, release, readiness level, performance claim, documentation deliverable, or checkpoint series.
- State the affected users and environments, constraints, and non-goals.
- Summarize the relevant current state and identify dependencies or compatibility boundaries.
- Order phases by risk: discovery before design, tests before risky behavior changes, compatibility before migration, measurement before optimization, and documentation before public readiness claims.
- Give each phase a goal, concrete tasks, acceptance criteria, validation evidence, and rollback or mitigation where relevant.
- Record risks and unknowns together with the first measurement or inspection that can reduce each one.
- Update durable plans as facts change, preserving useful decisions and marking superseded assumptions clearly.
Durable Plan Format
Include only sections that help execute or hand off the work:
- purpose and scope
- target users, environments, or release/readiness level
- constraints and non-goals
- current state and dependencies
- ordered phases
- acceptance and validation gates
- risks, unknowns, and mitigations
- rollback, checkpoint, or handoff slices
Validation Planning
- Derive commands and gates from
.github/copilot-instructions.md, the applicable.github/instructions/*.instructions.mdfiles,.github/workflows/ci.yml, and repository scripts instead of maintaining a second generic command list. - Choose the smallest focused check that can falsify each behavioral claim, then broaden validation according to the change's blast radius.
- Report correctness, security, performance, operability, compatibility, and documentation evidence separately; one gate does not prove the others.
- For performance claims, specify the platform, toolchain, feature flags, configuration, workload, dataset, baseline, and comparison criteria.
- For security or production-readiness work, include trust boundaries, resource limits, dependency risk, observability, rollback, and recovery where relevant.
Readiness Language
Do not describe Nacelle as production ready without scope. Prefer concrete conclusions such as:
- ready for internal users after the named gates pass
- safe for beta behind an explicit rollback mechanism
- ready for a measured low-risk workload with rollback documented
- not yet ready for public or regulated workloads
- requires a performance rebaseline before release
Checkpoints
When checkpoint commits are requested, define coherent slices such as plan or documentation, tests, architecture boundary, behavior change, migration, security control, performance profile, validation, or release preparation. Each checkpoint must build or test at the level required by its risk. Use Conventional Commits, and never create commits unless the user explicitly requests them.
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
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.

