strategize
Skill0 starsChanged 3 months agoMITView on GitHub
Turn a stated intent into the smallest bounded problem, outcome, scope and testable success gate before implementation begins. Use when an idea, request or detected issue needs a strategy packet before specifications or implementation.
4 other projects use a version of this.
Adopted by
Most recently taken up by
- linellazatin/skillstheir own version, first seen Oct 17, 2026
- hsantanna88/clo-authortheir own version, first seen Oct 9, 2026
- hugosantanna/clo-authortheir own version, first seen Oct 8, 2026
- Gaurav890/everything-agentic-engineeringtheir own version, first seen Sep 13, 2026
Other versions4 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 4
- hsantanna88/clo-author★ 262same name
- hugosantanna/clo-author★ 262same name
- Gaurav890/everything-agentic-engineering★ 1same name
- linellazatin/skills★ 1same 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 repository30 other files it gives its agents.
- auditSkill
- bootstrap-agent-contextSkill
- buildSkill
- closeSkill
- decision-logSkill
- feature-trackerSkill
- handoffSkill
- health-checkSkill
- idea-to-briefSkill
- live-state-preflightSkill
- portfolio-reviewSkill
- pre-commit-reviewSkill
- resolveSkill
- retrospectiveSkill
- session-summarySkill
- spec-packSkill
- stack-summarySkill
- testSkill
- the-loop-autonomySkill
- the-loop-autoSkill
- the-loop-cloudSkill
- the-loop-controlSkill
- the-loop-doctorSkill
- the-loop-endlessSkill
- the-loop-parallelSkill
- the-loop-setupSkill
- the-loop-skill-creatorSkill
- the-loopSkill
- the-loop-skill-plannerSkill
- the-loop-watchSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 2 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
2
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 19
Use for the first lifecycle stage, or when scope, objective or the definition of success has materially changed.
- Very specific: line 46
run ID, stage strategize, track and declared asset.
- Distinctive: line 68
Ask: does this solve the stated problem with the smallest sufficient scope, and could a different implementer satisfy the wording while …
“Common” is measured: kept by at least 6 in 10 of the 3 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
Strategize
Purpose
Provide the complete bundled fallback for lifecycle.strategize. Convert intent into a decision brief that is bounded enough to specify and verify. Do not draft implementation or hide a strategic fork.
Use when
Use for the first lifecycle stage, or when scope, objective or the definition of success has materially changed. An installed specialist may replace this fallback only through a recorded qualified route.
Required inputs
- Validated run ID, declared asset, immutable
codeornoncodetrack and current stage. - User intent, known constraints, supplied sources and relevant prior decisions.
- Frozen mission budget, active authority reference and exact mutation boundary.
- Current issues and evidence references, if this is a revised strategy.
- A requested capability and fallback route decision.
Reject the invocation when owner, lease, authority, asset, track or state cannot be established. Read-only analysis may continue only if the result is explicitly an unverified halt packet rather than a stage pass.
Procedure
- Restate the observed problem without adding unconfirmed facts.
- Define the desired outcome and the user or operator who benefits.
- Draw explicit in-scope, out-of-scope and later boundaries around one declared asset.
- List assumptions as confirmed, safely defaulted with a reversal condition, or unresolved human gates.
- Identify dependencies, authority needs, external effects, cost, privacy, legal and security risks.
- State success measures and turn each into a falsifiable done gate.
- Choose the smallest sufficient next unit: specification, one build slice, a non-code drafting unit, or a truthful halt.
- Record the bundled fallback as provider source and preserve every installed-candidate rejection reason.
Output contract
Return:
- run ID, stage
strategize, track and declared asset; - bounded problem statement and desired outcome;
- in-scope, out-of-scope and later lists;
- assumptions, constraints, risks and unresolved decisions;
- success measures and exact done gate;
- produced artifacts plus evidence and issue references;
- resulting gate state and recommended next stage or halt reason.
Evidence gate
Pass only when each material assumption has a confirmation, safe default with reversal condition, or named human gate, and each success measure has a verification method. Persist passing evidence before advancing. Missing or stale required evidence is UNVERIFIED, never passed.
Track requirements
For the code track, include repository identity, worktree state, intended isolation, live-state coverage and executable acceptance behavior. For the non-code track, include audience, format, factuality standard, source threshold, review method and publication boundary.
Safety and authority
Strategy may recommend outward work but cannot perform it. Expansion to another asset, audience, integration or materially broader success condition requires a new authority decision. Every side effect remains behind runtime preflight, durable intent and an unexpired matching lease.
Self-refutation
Ask: does this solve the stated problem with the smallest sufficient scope, and could a different implementer satisfy the wording while producing the wrong outcome? Tighten any ambiguous gate before passing.
Halt conditions
Halt on a strategic fork that changes the asset, authority, cost, legal exposure, privacy exposure or success definition; missing required source state; conflicting constraints; exhausted budget; detected stop; lost ownership; or an unavailable verification method. Include the last completed action, evidence gap and exact decision needed to continue.
Core execution does not require network access or the source checkout. The links below are optional public documentation.
References
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.

