assay-begin
Skill0 starsChanged 3 days agoApache-2.0View on GitHub
Use when starting work on an Assay unit of work (a GitHub issue id or an inline brief) and you need stakeholder proposals (technical + non-technical PDFs with diagrams) before planning. Triggers on "assay-begin", "ab", "ab bug 12", "ab feat skill-ingest", "begin full".
In this repository10 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- assay-begin-fastSkill
- assay-end-fastSkill
- assay-endSkill
- assay-nextSkill
- assay-reportSkill
- assay-worktreesSkill
- prd-generatorSkill
- prd-interviewSkill
- tech-planSkill
The file
We split this skill into the rules it gives an agent
3 rules. About 0 are common, 1 is distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 20
REQUIRED SUB-SKILL: Use assay-begin-fast for the base pipeline.
- Distinctive: line 22
Run its Phase 0 → Phase 4 and the ⛔ PRD review gate exactly as written.
- Very specific: line 43
Run assay-begin-fast's Phase 5 (tech-plan) then Phase 6 (implement, TDD via agents team).
≈ “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
Assay Begin (Full Track)
Overview
Same pipeline as assay-begin-fast, plus a proposal phase: after the PRD is
approved, produce diagrams and two review PDFs (technical + non-technical) for
stakeholders, get approval, then plan.
Invocation: ab <type> <id> — e.g. ab bug 12, ab feat skill-ingest.
Arguments and conventions are identical to assay-begin-fast.
Pipeline
REQUIRED SUB-SKILL: Use assay-begin-fast for the base pipeline.
Run its Phase 0 → Phase 4 and the ⛔ PRD review gate exactly as written.
Then, instead of going straight to tech-plan, insert Phase A below.
Phase A — Proposals (diagrams → PDFs)
Detailed steps: see references/proposals.md.
- Diagram — Use
excalidraw. Save todocs/planning/{slug}/diagrams/*.excalidraw. - Export — Use
excalidraw-to-svg. - Write two proposals in
docs/planning/{slug}/proposals/:<type>-<id>-technical-proposal.md— architecture, components, data flow, risks, effort.<type>-<id>-non-technical-proposal.md— problem, value, what changes, timeline, plain language.
- PDF — Use
md-to-pdf.
⛔ Approval gate — STOP
Present both PDFs. Wait for explicit approval before planning.
Final phases — Plan & implement
Run assay-begin-fast's Phase 5 (tech-plan) then Phase 6 (implement, TDD via
agents team).
Artifact layout
docs/planning/
├── _card/issue.md
├── {slug}/prd.md
├── {slug}/diagrams/*.excalidraw|.svg
├── {slug}/proposals/<type>-<id>-technical-proposal.{md,pdf}
├── {slug}/proposals/<type>-<id>-non-technical-proposal.{md,pdf}
└── {slug}/{aspect}/plan_*.mdCommon mistakes
| Mistake | Fix |
| Writing proposals before the PRD is approved | Phase A starts only after the first ⛔ gate |
| One proposal for both audiences | Always two |
Embedding .excalidraw instead of .svg | PDFs embed the exported SVGs |
| Overstating what a verdict proves | UNVERIFIED is never drawn as CLEAN; MALICIOUS requires a reproduced behavior |
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.

