pm-tech-scope
Skill2 starsChanged 4 months agoMITView on GitHub
Use when PM writes or reviews development tasks and must choose the smallest appropriate technology stack, language, runtime, environment, deliverable format, and escalation boundary. Applies especially when deciding between TypeScript, Python, static HTML/CSS/JS, existing project stack, scripts, games, prototypes, CLIs, automation, AI/ML, or production apps.
In this repository42 other files it gives its agents.
- architect-boundary-reviewSkill
- architect-decision-recordSkill
- architect-system-designSkill
- browser-playwright-checkSkill
- browser-useSkill
- code-search-navigationSkill
- controlled-emergence-observerSkill
- dev-code-locationSkill
- dev-small-scope-patchSkill
- dev-test-and-explainSkill
- eval-observation-writingSkill
- eval-promotion-adviceSkill
- eval-risk-gap-analysisSkill
- ops-log-diagnosisSkill
- ops-runtime-healthSkill
- ops-stuck-workflowSkill
- pm-acceptance-criteriaSkill
- pm-architecture-reviewSkill
- pm-delivery-planSkill
- pm-evolve-skillsSkill
- pm-long-horizon-planningSkill
- pm-priority-triageSkill
- pm-product-design-briefSkill
- pm-product-requirementsSkill
- pm-scope-controlSkill
- pm-solve-problemsSkill
- qa-regression-checkSkill
- qa-reproduce-issueSkill
- qa-verify-fixSkill
- run-local-command-checkSkill
- test-selectionSkill
- tm-delivery-governanceSkill
- tm-review-routingSkill
- tm-risk-dependencySkill
- ui-information-architectureSkill
- ui-requirementsSkill
- ui-usability-acceptanceSkill
- ui-visual-consistencySkill
- web-extractSkill
- web-researchSkill
- web-searchSkill
- windows-useSkill
The file
We split this skill into the rules it gives an agent
12 rules. About 0 are common, 8 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 10
Use this skill before PM dispatches a development task whose implementation language, runtime, framework, build chain, or delivery format …
- Distinctive: line 14
Do not infer the target task stack from the host repository stack.
- Very specific: line 16
Prefer static HTML/CSS/JS for standalone browser games, demos, prototypes, and simple interactive pages.
- Very specific: line 17
Prefer Python for automation, data processing, scripts, CLIs, local tooling, AI/ML workflows, quick backend utilities, and glue code.
- Very specific: line 18
Prefer TypeScript for existing TypeScript projects, long-lived frontend apps, shared packages, complex browser UI, or code that benefits …
- Distinctive: line 19
Follow the target project's existing stack for changes inside an existing project.
- Very specific: line 25
Use the structure in docs/skills/pm-playbook/tech-scope.md.
- Distinctive: line 29
Do not make TypeScript the default just because CodeFlowMu is TypeScript.
- Distinctive: line 30
Do not make Python the default just because it is a strong general-purpose AI-development language.
- Distinctive: line 31
Do not add a framework or build system for a task that can be delivered cleanly as a static file or small script.
- Distinctive: line 32
Do not hide deployment, runtime, or environment assumptions from DEV.
- Distinctive: line 33
Do not override explicit ADMIN or target-project constraints.
≈ “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.
Files
PM Tech Scope
When to use
Use this skill before PM dispatches a development task whose implementation language, runtime, framework, build chain, or delivery format is not already obvious from the target project.
Rules
- Do not infer the target task stack from the host repository stack.
- Choose the smallest appropriate stack for the requested deliverable.
- Prefer static
HTML/CSS/JSfor standalone browser games, demos, prototypes, and simple interactive pages. - Prefer
Pythonfor automation, data processing, scripts, CLIs, local tooling, AI/ML workflows, quick backend utilities, and glue code. - Prefer
TypeScriptfor existing TypeScript projects, long-lived frontend apps, shared packages, complex browser UI, or code that benefits from typed contracts. - Follow the target project's existing stack for changes inside an existing project.
- Require justification before adding a framework, build tool, backend, database, package manager, or new language.
- State how much technical discretion DEV has, and when DEV must report back before proceeding.
Required output
Use the structure in docs/skills/pm-playbook/tech-scope.md.
Forbidden actions
- Do not make TypeScript the default just because CodeFlowMu is TypeScript.
- Do not make Python the default just because it is a strong general-purpose AI-development language.
- Do not add a framework or build system for a task that can be delivered cleanly as a static file or small script.
- Do not hide deployment, runtime, or environment assumptions from DEV.
- Do not override explicit ADMIN or target-project constraints.
Minimal example
Deliverable: standalone browser mini-game
Preferred stack: static HTML/CSS/JS
Reason: no persistence, no shared package, no production build requirement
DEV discretion: may keep it single-file; must report before adding TypeScript or a bundlerDoes 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.

