sdd
Skill0 starsChanged 8 months agoApache-2.0View on GitHub
Run the Spec-Driven Development pipeline for a feature or change. Walks through SDD stages in order with enforced layer boundaries and feedback loops. Use when asked to build a feature end-to-end, propagate a change, fix a bug through SDD, or follow the SDD process. Accepts an optional starting layer as the first argument (e.g., "/sdd specification fix the caching bug").
22 other projects use a version of this.
Adopted by
Most recently taken up by
- Yeachan-Heo/oh-my-claudecodetheir own version, first seen Nov 15, 2026
- baekenough/oh-my-customcodetheir own version, first seen Nov 14, 2026
- AsiaOstrich/EngramGraphtheir own version, first seen Nov 8, 2026
- AsiaOstrich/universal-dev-standardstheir own version, first seen Nov 1, 2026
- totalfrank/skillstheir own version, first seen Oct 27, 2026
- monaccode/astromesh-sddtheir own version, first seen Oct 20, 2026
Used with
Projects with it also use bdd, migrate and 3 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.
TashanGKDSkillbdd
行为驱动开发(BDD)流程助手。用 Given-When-Then 描述验收标准,包含 Feature 文件管理、步骤定义实现。用户提到 BDD、验收测试、Gherkin 时使用。
Also in 3 projects that use this
tuistSkillmigrate
Migrates existing Xcode projects to Tuist generated workspaces with build and run validation, external dependency mapping, and migration checklists. Use when adopting Tuist for an existing app or converting a hand-edited Xcode project to generated projects.
Also in 4 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
Hugging FaceSkillimplement
Make tests pass. Invoke after /write-tests produces failing tests.
Also in 3 projects that use this
GoogleSkilltdd
Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.
Also in 4 projects that use this
Other versions22 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 22
- Yeachan-Heo/oh-my-claudecode★ 41ksame name
- siemens/ix★ 390same name
- SpillwaveSolutions/sdd-skill★ 99same name
- liatrio-labs/spec-driven-workflow★ 92same name
- AsiaOstrich/universal-dev-standards★ 84same name
- baekenough/oh-my-customcode★ 42same name
- dewil/ai-toolkit★ 9same name
- dewil/claude-toolkit★ 9same name
- artimath/effect-skills★ 8same name
- AsiaOstrich/EngramGraph★ 4same name
12 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 repository12 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- specification/CLAUDE.mdCLAUDE.md
- src/CLAUDE.mdCLAUDE.md
- tasks/CLAUDE.mdCLAUDE.md
- test/CLAUDE.mdCLAUDE.md
- cleanupSkill
- diagnoseSkill
- triageSkill
- writing-architectureSkill
- writing-specsSkill
- writing-tasksSkill
- writing-testsSkill
The file
Show its rules and text
We split this skill into the rules it gives an agent
22 rules. 0 are common, 12 are distinctive, and 10 are very specific to this project.
0
Common
Most of the 13 edited versions we read keep these.
12
Distinctive
This author's own choices. Worth a look.
10
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 43
If propagating from a user request that clearly defines the requirements, write or update the PRD in doc/requirements/ autonomously.
- Distinctive: line 44
If the requirements already exist and are sufficient, confirm with the user and skip to Stage 2.
- Distinctive: line 45
If the change requires judgment (e.g., scope decisions, priority trade-offs), present options with analysis and a recommendation.
- Very specific: line 50
If propagating from Stage 1, propagate to doc/features/ autonomously.
- Distinctive: line 51
If this is the starting stage, or if the change requires judgment beyond what the requirements prescribe, present options with analysis and …
- Distinctive: line 52
If a problem with the requirements is detected, do not edit requirements — surface the issue to the user and stop.
- Very specific: line 57
Read doc/architecture/data-models/expression-tree.md and doc/architecture/data-models/index-entities.md.
- Distinctive: line 59
If this is the starting stage, or if the change involves design decisions not prescribed by the feature doc, present options with analysis …
- Distinctive: line 60
If a problem is found in upstream documents, do not edit them — surface the issue to the user and stop.
- Distinctive: line 65
Read the parent architecture document.
- Very specific: line 67
If a problem is identified with the architecture, write a detailed description to doc/architecture/feedback/ and stop.
- Very specific: line 75
Read the blast radius from $CLAUDE_PROJECT_DIR/sdd-blast-radius if it exists.
- Distinctive: line 77
Write or update tests for the new/changed specifications within the blast radius.
- Distinctive: line 78
Do not change specifications.
- Very specific: line 79
Run python -m pytest test/ -x -q.
- Distinctive: line 81
Write the implementation to make tests pass.
- Very specific: line 82
Run python -m pytest test/ -x -q after each significant change.
- Very specific: line 92
Write to doc/architecture/feedback/, notify the user, and stop.
- Very specific: line 98
Remove $CLAUDE_PROJECT_DIR/sdd-blast-radius if it exists.
- Very specific: line 99
Check off completed tasks in tasks/ (update - [ ] to - [x]).
- Distinctive: line 100
If any feedback files still exist, notify the user and stop.
- Distinctive: line 102
Do not make a PR — the user decides when the branch is ready.
“Common” is measured: kept by at least 6 in 10 of the 13 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
Spec-Driven Development Pipeline
Execute the SDD pipeline for: $ARGUMENTS
Determine the starting stage
Parse the first word of the arguments. If it matches a layer name, start at that stage and skip earlier stages. Otherwise, start at Stage 1.
| First word | Start at |
requirements | Stage 1 |
features | Stage 2 |
architecture | Stage 3 |
specification | Stage 4 |
tests | Stage 5 |
implementation | Stage 5 |
| (anything else) | Stage 1 (full pipeline) |
Note: implementation maps to Stage 5 (tests first), enforcing TDD. To skip tests entirely, use the /implementation phase command directly instead of /sdd.
Work through the stages below starting from the determined stage. At each stage, set the phase to enforce layer boundaries. Do not invent requirements or infer unnecessary details — ask the user when ambiguities exist.
Autonomy rules
Human-in-the-loop layers (doc/requirements/, doc/features/, doc/architecture/):
- Propagating downward from the stage above (e.g., requirements→features, features→architecture): proceed autonomously.
- Originating changes (writing initial content, fixing a gap found during triage, or making changes NOT derived from the stage immediately above): present 2-3 options with critical analysis and a recommendation. Wait for the user to approve before editing.
Autonomous layers (specification/, test/, src/):
- Proceed without human intervention.
- After 3 feedback cycles, stop and present the situation to the user. This prevents infinite loops. Summarize what was attempted, what keeps failing, and ask for direction.
Stage 1: Requirements
- Run:
echo "requirements" > $CLAUDE_PROJECT_DIR/sdd-layer - If propagating from a user request that clearly defines the requirements, write or update the PRD in
doc/requirements/autonomously. - If the requirements already exist and are sufficient, confirm with the user and skip to Stage 2.
- If the change requires judgment (e.g., scope decisions, priority trade-offs), present options with analysis and a recommendation. Wait for approval.
Stage 2: Features
- Run:
echo "features" > $CLAUDE_PROJECT_DIR/sdd-layer - If propagating from Stage 1, propagate to
doc/features/autonomously. - If this is the starting stage, or if the change requires judgment beyond what the requirements prescribe, present options with analysis and a recommendation. Wait for approval.
- If a problem with the requirements is detected, do not edit requirements — surface the issue to the user and stop.
Stage 3: Architecture
- Run:
echo "architecture" > $CLAUDE_PROJECT_DIR/sdd-layer - Read
doc/architecture/data-models/expression-tree.mdanddoc/architecture/data-models/index-entities.md. - If propagating from Stage 2, propagate to
doc/architecture/autonomously. - If this is the starting stage, or if the change involves design decisions not prescribed by the feature doc, present options with analysis and a recommendation. Wait for approval.
- If a problem is found in upstream documents, do not edit them — surface the issue to the user and stop.
Stage 4: Specifications
- Run:
echo "specification" > $CLAUDE_PROJECT_DIR/sdd-layer - Read the parent architecture document.
- Propagate architecture down to
specification/. - If a problem is identified with the architecture, write a detailed description to
doc/architecture/feedback/and stop. Notify the user — architecture changes require human approval. - Record the blast radius — write changed spec filenames to
$CLAUDE_PROJECT_DIR/sdd-blast-radius:echo "specification/channels.md specification/storage.md" > $CLAUDE_PROJECT_DIR/sdd-blast-radius
Stage 5: Tests and Implementation
This stage follows TDD: write failing tests first, then implement until tests pass. Track feedback cycles (any return to step 1 or 3 from a feedback resolution counts as one cycle).
- Read the blast radius from
$CLAUDE_PROJECT_DIR/sdd-blast-radiusif it exists. - Run:
echo "tests" > $CLAUDE_PROJECT_DIR/sdd-layer - Write or update tests for the new/changed specifications within the blast radius.
- Do not change specifications. If a spec problem is found, go to step 9.
- Run
python -m pytest test/ -x -q. New tests covering the change should fail. Existing tests may pass or fail. - Run:
echo "implementation" > $CLAUDE_PROJECT_DIR/sdd-layer - Write the implementation to make tests pass. Do not change tests or specifications.
- Run
python -m pytest test/ -x -qafter each significant change. When all tests pass, proceed to Completion. - If a spec problem is found (during tests or implementation):
- Run:
echo "specification" > $CLAUDE_PROJECT_DIR/sdd-layer - Fix the specification. Delete the feedback file.
- Increment feedback cycle count. Return to step 2.
- Run:
- If a test problem is found (during implementation):
- Run:
echo "tests" > $CLAUDE_PROJECT_DIR/sdd-layer - Fix the test. Delete the feedback file.
- Increment feedback cycle count. Return to step 6.
- Run:
- If an architecture problem is found:
- Write to
doc/architecture/feedback/, notify the user, and stop.
- Write to
- After 3 feedback cycles, stop and present the situation to the user: summarize what was attempted, what keeps failing, and ask for direction.
Completion
- Run:
echo "free" > $CLAUDE_PROJECT_DIR/sdd-layer - Remove
$CLAUDE_PROJECT_DIR/sdd-blast-radiusif it exists. - Check off completed tasks in
tasks/(update- [ ]to- [x]). - If any feedback files still exist, notify the user and stop.
- Report what was done and which files were changed.
- Do not make a PR — the user decides when the branch is ready.
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.

