pipeline-steps
Skill13 starsChanged 5 months agoMITView on GitHub
Map of pipeline steps (0-19) and jobs with registry rules; detailed per-step instructions live in references/steps.md. Read this whenever the PM calls a pipeline command (/analyze-cjm, /validate-problems, …) or a job, then read the matching section of references/steps.md.
In this repository23 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- ambiguity-resolverSkill
- challengeSkill
- deep-thinkSkill
- design-critique-templateSkill
- experiment-designSkill
- ingestSkill
- interview-analysisSkill
- multi-source-signal-synthesiserSkill
- next-advisorSkill
- post-launch-reviewSkill
- problem-structuringSkill
- product-requirements-docSkill
- setup-initiativeSkill
- solution-scoringSkill
- strategic-narrative-generatorSkill
- system-design-docSkill
- technical-spec-documentSkill
- tracking-and-funnelsSkill
- ui-pattern-librarySkill
- user-persona-builderSkill
- user-story-generatorSkill
- user-testingSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 1 is distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈1
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
Every job runs standalone: no initiative → work on chat context, type evidence INFERRED, offer to persist afterwards.
≈ “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
Pipeline Step Instructions
Navigation layer: jobs map + registry rules here, per-step details in
references/steps.md (read only the section you are executing).
Jobs → steps. Jobs are the primary interface (CLAUDE.md → JOBS CATALOG):
/hypotheses → steps 1–2 · /brief → 4/5/11 · /validate → 6 ·
/solutions → 7 · /sketch → 8 · /tickets → create-tickets ·
/ingest → skill ingest · /next → skill next-advisor ·
/challenge → skill challenge · /deep-think → skill deep-think.
Every job runs standalone: no initiative → work on chat context, type
evidence INFERRED, offer to persist afterwards; initiative exists → read and
write its registry and artifacts as described per step.
Hypothesis registry (all steps). Hypothesis STATE (status, evidence type,
confidence, sources, history) lives in output/hypotheses.json — manage it via
python3 tools/scripts/hypotheses.py (add / set / validate / render).
set records history automatically. Narrative markdown (hypotheses.md,
validated-hypotheses.md) stays authored prose and must not contradict the
registry. After changing the registry run hypotheses.py render <dir> to
refresh output/registry.md. Legacy initiatives: convert once with
python3 tools/scripts/migrate-hypotheses.py <dir>.
Step index
Details for every step live in references/steps.md — read the section
for the step you are executing (table of contents at the top; don't load
other steps, they aren't needed).
| # | Command | Type | Note |
| 0 | /setup-initiative | Core | |
| 1 | /analyze-cjm | Core | |
| 2 | /synthetic-research | Recommended | |
| 3 | /competitor-research | Recommended | |
| 4 | /generate-research | Recommended | |
| 5 | /create-survey-audience | Optional | |
| 6 | /validate-problems | Core | |
| 7 | /solution-hypotheses | Core | |
| 8 | /sketch-solution | Core | |
| 8.5 | /user-test-concept | Optional; alias for user-testing concept mode | |
| 9 | /review-design | Recommended | |
| 10 | /create-presentation | Core | Problem Research Report |
| 11 | /create-design-brief | Recommended | |
| 12 | /estimate-with-dev | Core | |
| 13 | /finalize-prd | Core | |
| 14 | /design-ab-test | Recommended | |
| 15 | /create-gate2-presentation | Core | Solution Research Report |
| — | /create-tickets | after Gate 2 | push to tracker via MCP |
| 16 | /analyze-ab-test | Recommended | |
| 17 | /plan-gtm | Core | |
| 18 | /create-gtm-materials | Optional | |
| 19 | /support-task | Optional |
Gates (steps 10, 15) have machine preconditions — validate-evidence.py
--gate must be CLEAR before assembling a deck; offer /challenge to
rehearse. External handoffs (steps 4, 5, 11, 12, 14, 16, 18, 19) create
dependencies[] entries with owner + deadline.
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.

