flow
Skill5 starsChanged 29 days agoMITView on GitHub
Use when organizing a multi-step task, choosing the next lifecycle phase, checking delivery readiness, or handing work to another session. Routes software and other deliverables through proportionate evidence and verification without requiring a particular stack or a complete process for every task.
33 other projects use a version of this.
Adopted by
Most recently taken up by
- phuthuycoding/kanban-flowtheir own version, first seen Nov 8, 2026
- baodhg/FLOWtheir own version, first seen Nov 8, 2026
- jocarrd/crux-agentstheir own version, first seen Nov 8, 2026
- cofin/flowtheir own version, first seen Nov 7, 2026
- retospect/precis-mcptheir own version, first seen Nov 6, 2026
- lidaye910416/prompt-polishtheir own version, first seen Nov 1, 2026
Used with
Projects with it also use grill, implement and 5 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.
renatorozasSkillgrill
Adversarial code review. Don't let me ship until the changes pass your scrutiny.
Also in 3 projects that use this
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 5 projects that use this
SentrySkillreview
Fixture review skill.
Also in 6 projects that use this
AnthropicSkillstatus
Case status summary by audience — client-facing (plain language), internal (for the professor), or court-ready (formal caption format per local rules). Same facts, different framing and depth. Use when a student needs to update the client, brief the professor, or prepare a court status report.
Also in 3 projects that use this
BlockSkillplan
Draft a TDD, PRD, or lightweight plan in the conversation without committing it.
Also in 3 projects that use this
AWSSkillship
Finalize dev work on an issue branch — update docs, push, and open a PR.
Also in 3 projects that use this
Other versions33 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 33
- react/react★ 252ksame name
- facebook/react★ 252ksame name
- software-mansion/react-native-audio-api★ 856same name
- simota/agent-skills★ 96same name
- panayiotism/claude-harness★ 79same name
- rainday/smart-blog-skills★ 35same name
- cofin/flow★ 19same name
- basezh/agent-skills-on-base★ 15same name
- retospect/precis-mcp★ 11same name
- foryouself83/harness-tier★ 10same name
23 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 repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- boostSkill
- data-migration-best-practicesSkill
- ddd-best-practicesSkill
- design-patterns-best-practicesSkill
- fp-best-practicesSkill
- infrastructure-designSkill
- oop-best-practicesSkill
- refactoring-best-practicesSkill
- rest-api-best-practicesSkill
- tdd-best-practicesSkill
The file
Files
Flow
Identify the requested outcome, the current phase, and what would demonstrate completion. Enter at that phase rather than restarting discovery. Use project-local instructions and resources; run boost only when the resource setup itself needs work.
When explicitly invoked without additional instructions, recover the latest authorized task from the conversation and project artifacts, check the actual working state, and complete the next coherent unit through verification. If no intended task can be established, ask for the desired outcome. Additional instructions select the task or phase; they do not authorize unrelated external actions.
| Need | Next action and evidence |
| Discover or research | Resolve consequential uncertainty with actual artifacts or primary sources; distinguish evidence from assumptions. |
| Define | Record the outcome, audience, scope, and checkable acceptance criteria at the project's existing location. |
| Plan | Order dependent work in small verifiable units. Scale the plan to the task and preserve the user's constraints. |
| Execute | Complete one coherent unit, observe its result, and adjust based on evidence. Preserve unrelated work. |
| Verify | Use checks that can distinguish a plausible wrong result. Choose the required evidence for the artifact and risk. |
| Review | Compare the actual result with the requested scope and existing conventions. Separate confirmed defects from suggestions. |
| Deliver | Produce the authorized final artifact and record material limits. Publication, commits, and external actions require the applicable authorization. |
| Operate or maintain | Observe the declared success/failure signals; diagnose deviations and make scoped corrections. |
| Migrate or retire | Identify consumers, preserve required compatibility, and plan recovery before removing an old path. |
| Resume or hand off | Record durable decisions, artifact paths, working state, verification results, unresolved questions, and the next action. |
For implementation, bugs, release readiness, operations, or persisted-data migration, read references/software.md. For documents, analysis, research, or other deliverables, read references/other-work.md. Do not load both branches automatically.
Reuse successful checks while their evidence remains valid. Investigate a new failure rather than weakening the criterion. Report a limitation when the required check cannot run. Routine reversible decisions stay autonomous; ask about an ambiguity only when it changes a consequential outcome or authorization.
At a session boundary, link to existing specs and artifacts instead of duplicating them. Keep summaries concise and redact sensitive data. This skill coordinates phases; it does not impose a language, framework, architecture, test percentage, issue tracker, model roster, or mandatory delegation.
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.