phase
Skill11 starsChanged 10 days agoMITView on GitHub
Show current phase, switch phases, list phase artifacts. Use when the user says "what phase are we in", "switch to the design phase", "what has been produced so far", or invokes /phase.
3 other projects use a version of this.
Adopted by
Most recently taken up by
- transitive-bullshit/skillstheir own version, first seen Oct 13, 2026
- vercel-labs/phasetheir own version, first seen Oct 13, 2026
- winchxyz/idea-to-buildtheir own version, first seen Jun 9, 2026
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- vercel-labs/phase★ 98same name
- winchxyz/idea-to-build★ 9same name
- transitive-bullshit/skills★ 5same 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 repository44 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- analyze-dataSkill
- brainstormingSkill
- craft-lessonSkill
- create-agentSkill
- create-skillSkill
- customize-agentSkill
- customize-skillSkill
- designSkill
- deslopSkill
- developSkill
- discovery-reportSkill
- elicitationSkill
- empathy-mapSkill
- explore-ideaSkill
- grill-meSkill
- help-meSkill
- humanizeSkill
- incidentSkill
- iterateSkill
- journey-mapSkill
- jtbdSkill
- kanbanSkill
- launchSkill
- legal-safety-auditSkill
- maintenance-executeSkill
- maintenance-planSkill
- memorySkill
- motionSkill
- planSkill
- research-planSkill
- retroSkill
- reviewSkill
- root-causeSkill
- round-tableSkill
- shape-upSkill
- shut-upSkill
- statusSkill
- teach-meSkill
- testSkill
- unpack-problemSkill
- validate-ideaSkill
- validation-patternsSkill
The file
We split this skill into the rules it gives an agent
3 rules. 0 are common, 1 is distinctive, and 2 are very specific to this project.
0
Common
Most of the 3 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 43
Read artifacts/output/pipeline-state.json (or execute node .agents/scripts/orchestrator_state.js status) to read the canonical …
- Very specific: line 45
If not initialized, fall back to reading artifacts/memory/project-context.md for the current phase, or infer from the latest artifact in …
- Distinctive: line 79
If the user requests a phase switch:
“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
Phase — Pipeline Phase Control
What this skill does
Displays the current phase in the product pipeline, allows switching between phases, and lists the artifacts produced in each phase.
When to use
- "What phase are we in?"
- "Switch to design phase"
- "Show me what's been produced so far"
- "What phase should I be in for X?"
Pipeline phases
| Phase | Skill | Key Output |
| -1: Validation | validate-idea | Validation brief (GO/RESHAPE/NO-GO) |
| 0: Discovery | explore-idea | Idea brief |
| 1: Research | explore-idea | Market analysis, personas, competitive landscape |
| 2: Strategy | design | PRD, user stories, product spec |
| 3: Architecture | design | ADRs |
| 4: Planning | plan | Execution plan, task estimates, Kanban |
| 5: Execution | develop | Working, tested feature |
| 6: Launch | launch | Shipped feature in production |
| 7: Iteration | iterate | Measured improvement |
| 8: Documentation | (cross-cutting) | Current docs |
| 9: Retrospective | retro | Action items for improvement |
| Any: Incident | incident | Mitigated incident, RCA |
Workflow
Step 1: Detect current phase
Read artifacts/output/pipeline-state.json (or execute node .agents/scripts/orchestrator_state.js status) to read the canonical "current_phase".
If not initialized, fall back to reading artifacts/memory/project-context.md for the current phase, or infer from the latest artifact in artifacts/output/:
01-discovery/has content → discovery02-research/has content → research03-strategy/has content → strategy04-architecture/has content → architecture05-planning/has content → planning05-execution/has content → execution06-launch/has content → launch07-iteration/has content → iteration08-documentation/has content → documentation09-retro/has content → retro
Step 2: Report
Answer the question asked, and do not re-render the snapshot.
If the user asked "what phase are we in?" — say the phase, its status, and the next action:
## Current Phase: {phase name}
**Status:** {status from pipeline-state.json's phases[phase]}
**Next:** {Run `node .agents/scripts/orchestrator_state.js next`}If the user asked "what's been produced?" — list the current phase's artifacts and versions.
For anything wider — blockers, change requests, the last session, memory health, artifacts across
all phases — point at /status rather than restating it. This skill used to render a full report
whose every field /status already produces, in a different shape, from the same file. Two renderings
of one source drift, and a reader cannot tell which is current. /status is the snapshot; this skill
owns exactly one thing it does not: switching the phase (Step 3).
Step 3: Switch phase (on request)
If the user requests a phase switch:
- Run:
(Note: This programmatically updates the current_phase, records it in the history, sets appropriate in-progress timestamps, and automatically syncsnode .agents/scripts/orchestrator_state.js set-phase --phase {targetPhase}artifacts/memory/project-context.md'sPhase:field). - Log the change to
artifacts/memory/active-decisions.md - Load the corresponding skill for the new phase
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.

