srs-to-sd
Skill0 starsChanged 52 days agoMITView on GitHub
Convert an approved SRS into a Solution Design and drive the hybrid spec-flow. Use this skill when the user mentions an SRS, a Solution Design (SD), "convert SRS to SD", starting a feature from a spec, re-syncing after Product changed the SRS, or running a fix/enhance loop on an implemented feature. Routes to the right spec-flow command.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- tranquocthong/claude-spec-flowword for word, first seen Sep 22, 2026
Other versions1 project uses a version of this.
Word for word · 1
- tranquocthong/claude-spec-flow★ 0100% same
Edited · 0
None found.
Wrote their own version · 0
None found.
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 repository2 other files it gives its agents.
- commitSkill
- manual-testSkill
The file
Files
spec-flow — SRS → SD → implement → verify → ship
Routes to the right command and enforces the gates.
Route by intent
| User intent | Command |
| "convert this SRS to SD", start a feature from an SRS | /sf:ingest <srs> |
| have only an idea/description, no SRS file | /sf:ingest (no file) or /sf:ingest --idea "<seed>" — it interviews you, writes srs/<feature>.md, then ingests |
| generate manual-test checklist from the SD | /sf:checklist <feature> |
| implement the feature | /sf:phase <feature> |
| Product changed the SRS, propagate it | /sf:resync <srs_v2> |
| want to change the spec / enhance after impl | /sf:change "<desc>" --type fix|enhance |
Non-negotiable gates
/sf:ingestNEVER implements — ingest (incl. its interview mode) outputs only the SRS + SD + trace, then STOPS at the SD review gate. Discussing a feature is not permission to code it. Application code happens only in/sf:phase, after the SD is approved. If a build/TDD skill is also loaded, this gate wins for the ingest step.- No tasks before approval — never
parse_prdwhile SD hasTODO:MANUAL-REVIEWmarkers. - CHECKLIST before BUILD — every feature has a
CHECKLIST.yamlbefore the first task is implemented. - manual-test before done — task goes
review → doneonly afterrun-checklist.shsmoke passes; phase ships only when regression passes (VERIFICATION.md status: passed). - SD is the source of truth — change SD first, then let trace +
update --frompropagate. Never patch code without patching the SD.
Dependencies
- Bundled, zero-network: manual-test skill (
skills/manual-test/scripts/*),bin/flow-tools.cjs, and the native task engine MCP server (bin/mcp-server.js, wired via.mcp.json) — no external package fetch, uses the keylessclaude-codeprovider by default (no API key).
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.