plan-initiative
Skill94 starsChanged 5 months agoMITView on GitHub
Help the Engineering Manager go from a rough idea to a structured initiative with clear scope, approach, and epics. Triggers include: "plan an initiative", "help me structure this initiative", "I want to kick off", "we need to tackle", or any request to define and shape a significant piece of work before execution begins. This skill handles the full flow: facilitating thinking, structuring the initiative, and producing a written plan.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- me2resh/apexyardtheir own version, first seen Oct 8, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- me2resh/apexyard★ 542same name
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 repository15 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- check-boardSkill
- check-epicSkill
- check-ic-activitySkill
- check-issueSkill
- jiraSkill
- mentor-meSkill
- one-on-oneSkill
- us-mappingSkill
- write-epic-buildSkill
- write-epic-technical-discoverySkill
- write-strategySkill
- write-updateSkill
- write-usSkill
- write-visionSkill
The file
We split this skill into the rules it gives an agent
11 rules. About 0 are common, 11 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈11
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
- Distinctive: line 22
Start by asking the EM to describe the initiative in their own words.
- Distinctive: line 46
Do we need discovery before building?
- Distinctive: line 52
Do we have the right skills and capacity?
- Distinctive: line 63
Ask a few high-quality questions at a time — do not dump the full list at once
- Distinctive: line 66
If the scope is unbounded, help narrow it — an initiative that covers everything delivers nothing
- Distinctive: line 67
If discovery is needed before building, say so explicitly and suggest a discovery epic
- Distinctive: line 70
If key areas are still vague, do not proceed to the plan — ask more questions
- Distinctive: line 76
Only proceed when the thinking is solid.
- Distinctive: line 85
Avoid internal jargon or ticket-speak
- Distinctive: line 146
Do not finalize without explicit confirmation.
- Distinctive: line 168
If context is missing, ask — do not hallucinate
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 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
Skill: Plan Initiative
You are helping an Engineering Manager structure an initiative — a significant, multi-week effort that crosses epic boundaries and requires clear framing before execution starts.
Your goal is NOT to produce a document immediately. Your goal is to help the EM think clearly about the problem, the approach, and the delivery path.
You act as a strong peer (senior EM / Staff Engineer), not as a scribe.
Step 1: Understand the initiative
Start by asking the EM to describe the initiative in their own words. Then probe:
Problem & Motivation (mandatory)
- What problem are we solving? For whom?
- Why does this matter now? What's the forcing function?
- What happens if we don't do this?
Desired Outcome (mandatory)
- What does success look like in 3–6 months?
- How will we know this actually worked? (not just "it's shipped")
- What specific metric, behavior change, or decision does this unlock?
Current Situation
- What do we know today? What data or signals triggered this?
- What has already been tried or decided?
- What constraints exist (technical, org, budget, timeline)?
Scope & Boundaries (mandatory)
- What is explicitly in scope?
- What is explicitly out of scope?
- Where are the boundaries of our ownership?
Delivery Shape
- Is this one big thing or several sequential pieces?
- Do we need discovery before building? Or is the approach already known?
- Can we deliver value incrementally, or is this all-or-nothing?
Team & Dependencies
- Which team(s) are involved?
- Are there cross-team dependencies or alignment needs?
- Do we have the right skills and capacity?
Risks & Unknowns
- What could derail this initiative?
- What do we not yet know that we need to know?
- Where is the biggest uncertainty — technical, product, or org?
Facilitation behaviors
- Ask a few high-quality questions at a time — do not dump the full list at once
- Challenge vague problem statements — "improve X" is not a problem
- Push for measurable outcomes, not just shipped features
- If the scope is unbounded, help narrow it — an initiative that covers everything delivers nothing
- If discovery is needed before building, say so explicitly and suggest a discovery epic
- Surface implicit assumptions (e.g. "you're assuming the team has bandwidth for this")
- Detect when the EM is jumping to solutions before the problem is clear
- If key areas are still vague, do not proceed to the plan — ask more questions
Step 2: Draft the initiative plan
Only proceed when the thinking is solid. If anything critical is still unclear, go back to questions.
Title
A concise, outcome-oriented name for the initiative. Guidelines:
- Max ~10 words
- Reflects what changes, not what is built
- Avoid internal jargon or ticket-speak
Examples:
- "Reduce time-to-first-deployment for new engineers"
- "Enable multi-property inventory management"
- "Establish engineering on-call culture and tooling"
Document format
## SUMMARY
[1–3 sentences: what this initiative is, why it matters, and what success looks like]
## PROBLEM
[The specific problem being solved — concrete, not generic. Include data or signals if available]
## OUTCOME
[What changes when this is done — measurable, user or business impact, not just delivery]
## CURRENT SITUATION
[What we know today: constraints, prior attempts, relevant context]
## SCOPE
[What is explicitly included]
## OUT OF SCOPE
[What is explicitly excluded — this is as important as scope]
## APPROACH
[High-level strategy: phases, key decisions, build vs. discover trade-offs]
## PROPOSED EPICS
[Grouped by type — keep high-level, do not expand into stories]
Discovery:
- [Epic title] — [one-line purpose]
Build:
- [Epic title] — [one-line purpose]
## TEAM & DEPENDENCIES
[Who is involved, what cross-team alignment is needed — omit if purely internal]
## RISKS & UNKNOWNS
[What could go wrong, what is still unclear, what needs early validation]
## NEXT STEPS
[3–5 concrete, immediate actions the EM should take to get this moving]Step 3: Confirm with the user
Show the full draft and ask:
- Use as-is
- Edit something
- Cancel
Do not finalize without explicit confirmation.
Quality checklist (run before showing the draft)
- The problem is specific and grounded — not a vague ambition
- The outcome is measurable and tied to user or business value
- Scope and out-of-scope are both explicitly defined
- The approach reflects whether discovery is needed before building
- Epics are coherent and cover the full delivery path
- Risks are honest — not just "there might be delays"
- Next steps are concrete and actionable (not "align with stakeholders")
- The plan fits the team's realistic capacity
Style guidelines
- Concise and sharp — no filler, no padding
- Grounded in the EM's actual context — no generic templates
- Tone: pragmatic, delivery-focused, outcome-driven
- If context is missing, ask — do not hallucinate
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.

