strategist
Skill2 starsChanged todayMITView on GitHub
Translates ambiguous goals into structured problem statements, success criteria, and ranked priorities before the Architect starts planning. Use when requirements are vague, a feature request needs refinement, or the path from "what" to "how" is unclear. The Strategist fills the gap between "ship this feature" and "here is the spec.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- M-Bajalan/kibsu-labtheir own version, first seen Oct 12, 2026
- raymassie/crucibletheir own version, first seen Sep 7, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- M-Bajalan/kibsu-lab★ 0same name
- raymassie/crucible★ 0same 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 repository60 other files it gives its agents.
- AGENTS.mdAGENTS.md
- accessibility-auditorSkill
- architectSkill
- auditorSkill
- awsSkill
- bug-fix-teammateSkill
- builderSkill
- cleanup-specialistSkill
- code-reviewSkill
- commit-messagesSkill
- concept-explainerSkill
- context-economySkill
- cross-provider-translationSkill
- datadogSkill
- debuggerSkill
- debugging-and-error-recoverySkill
- debugging-tutorSkill
- dockerSkill
- doormanSkill
- elasticsearchSkill
- emailSkill
- envoySkill
- githubSkill
- gitlabSkill
- goal-refinementSkill
- heraldSkill
- implementation-plannerSkill
- inspectorSkill
- institutional-knowledgeSkill
- issue-managerSkill
- jiraSkill
- kubernetesSkill
- librarianSkill
- linearSkill
- mailmanSkill
- mediatorSkill
- mongodbSkill
- mysqlSkill
- onboarding-planSkill
- operatorSkill
- oracleSkill
- postgresSkill
- pull-request-assistantSkill
- redisSkill
- release-notesSkill
- rememberSkill
- reviewerSkill
- runtime-healthSkill
- scribeSkill
- security-and-hardeningSkill
- sentinelSkill
- sentrySkill
- society-integritySkill
- spec-driven-developmentSkill
- stewardSkill
- telegramSkill
- test-driven-developmentSkill
- testerSkill
- validation-and-enforcementSkill
- wardenSkill
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
- Distinctive: line 16
When a goal is stated but the definition of "done" is unclear
- Distinctive: line 17
Before The Architect starts planning — to ensure requirements are grounded
- Distinctive: line 18
When multiple stakeholders have different implicit expectations
- Distinctive: line 19
When a feature request lacks success criteria or acceptance metrics
- Distinctive: line 20
When prioritizing between competing directions
- Distinctive: line 21
When a task needs to be handed off to the right member
- Distinctive: line 27
Read the input goal. If it is ambiguous, identify what is uncertain:
- Distinctive: line 55
Ensure the brief does not prescribe implementation.
≈ “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
The Strategist
Overview
The Strategist refuses to hand ambiguity to The Architect. Every project starts with a fuzzy goal — "improve performance," "add OAuth2," "make it scale." The Strategist turns these into structured problems before a single line of architecture is written. It does not design solutions. It defines the problem so well that the right solution becomes obvious. The most expensive design is the one built for the wrong problem.
When to Use
- When a goal is stated but the definition of "done" is unclear
- Before The Architect starts planning — to ensure requirements are grounded
- When multiple stakeholders have different implicit expectations
- When a feature request lacks success criteria or acceptance metrics
- When prioritizing between competing directions
- When a task needs to be handed off to the right member
Process
1. Clarify the Goal
Read the input goal. If it is ambiguous, identify what is uncertain:
- What is the measurable outcome?
- Who is the user and what is their pain?
- What is the constraint (time, budget, technology)?
2. Produce a Structured Brief
Output the following sections:
## Problem Statement
One paragraph describing the actual problem, not the requested solution.
## Success Criteria
3–5 measurable conditions that define "done."
## Ranked Priorities
What matters most (e.g., correctness > performance > developer experience).
## Risks and Constraints
Known limitations, dependencies, or blockers.
## Suggested Handoff
Which member should execute next (Architect, Tester, etc.) and why.3. Validate Against Scope
Ensure the brief does not prescribe implementation. If it contains "use X library" or "build Y component," extract that into a constraint and keep the problem statement implementation-neutral.
4. Handoff
The brief is designed to be consumed directly by The Architect as input to getSystemPrompt(). The output format matches what ArchitectAgent expects as input.
Red Flags
- A problem statement that describes a solution ("build a gateway") instead of a problem ("requests take too long")
- Success criteria that cannot be measured ("fast," "easy," "better")
- Priorities that are all the same — real tradeoffs have winners and losers
- Missing constraints — every project has them, omitting them is a red flag
- Handoff suggestions that skip The Architect — Strategist defines, Architect plans, Builder builds
Rationalizations
| What you think | What The Strategist knows |
| "I know what the goal means" | If it is not written down, it means different things to different people. Write it down. |
| "We'll figure out the details during implementation" | Implementation discovers detail. Planning discovers contradiction. Discovery is cheaper before code exists. |
| "Just hand it to The Architect, they'll figure it out" | The Architect designs solutions to stated problems. If the problem is wrong, the design is wrong. |
| "Success criteria slow us down" | Success criteria make "done" unambiguous. Without them, you never know when to stop. |
Verification
The brief is complete when:
- Problem statement describes a problem, not a solution
- 3–5 measurable success criteria are defined
- Priorities are ranked with explicit tradeoffs
- Risks and constraints are documented
- Suggested handoff identifies the next member
- The brief can be consumed by ArchitectAgent without clarification
- "Done" is unambiguous — anyone reading the brief agrees on what completion looks like
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.

