spec
Skill0 starsChanged 5 months agoMITView on GitHub
Generate a code-grounded technical spec — Staff Engineer and Design Lead review the codebase together, then produce a combined technical + UX spec.
175 other projects use a version of this.
Adopted by
Most recently taken up by
- go-sphere/skillstheir own version, first seen Nov 16, 2026
- chrisezedi/claude-skillstheir own version, first seen Nov 16, 2026
- ByteLab-dev-ar/skills-proyectostheir own version, first seen Nov 16, 2026
- devonbweaver/Spec-Looptheir own version, first seen Nov 16, 2026
- pushkincode/skillstheir own version, first seen Nov 16, 2026
- timursafiullin/aodtheir own version, first seen Nov 15, 2026
Used with
Projects with it also use backprop, ios-clean and 10 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.
JuliusBrusseeSkillbackprop
Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.
Also in 4 projects that use this
Saqlain-811Skillios-clean
Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)
Also in 5 projects that use this
Saqlain-811Skillios-fix
Autonomous iOS bug fixer. (gstack)
Also in 5 projects that use this
bastosSkillios-design-review
Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".
Also in 5 projects that use this
ShreyRaviSkillplan-tune
Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.
Also in 7 projects that use this
timurgaleevSkilldocument-generate
Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.
Also in 6 projects that use this
- +2 more from Saqlain-811
Other versions175 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 175
- garrytan/gstack★ 142ksame name
- getsentry/sentry-react-native★ 1.8ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- kdlbs/kandev★ 1.1ksame name
- getsentry/sentry-dart★ 877same name
- poshan0126/dotclaude★ 871same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- SparkDevNetwork/Rock★ 701same name
- strands-agents/box★ 547same name
- hyperlink-academy/leaflet★ 527same name
165 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.
The file
We split this skill into the rules it gives an agent
11 rules. 0 are common, 8 are distinctive, and 3 are very specific to this project.
0
Common
Most of the 151 edited versions we read keep these.
8
Distinctive
This author's own choices. Worth a look.
3
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 14
Code-grounded only: Only reference architecture, patterns, and constraints you have actually read.
- Distinctive: line 16
Read first, spec second: Every section must be informed by actual codebase reading.
- Distinctive: line 22
Read CLAUDE.md if it exists.
- Very specific: line 23
Read STRATEGY.md if it exists.
- Distinctive: line 24
If the user has not described what to spec, ask them for the feature or problem now.
- Distinctive: line 33
Read those files. For large codebases, read the most representative files — entry points, relevant models, key components.
- Distinctive: line 38
Test coverage in the affected areas
- Distinctive: line 132
All open questions from both perspectives, with owner and blocking status:
- Distinctive: line 147
After producing the complete spec above, save it to the project:
- Very specific: line 149
Create docs/specs/ if it doesn't exist.
- Very specific: line 151
Write the full spec to: docs/specs/YYYY-MM-DD-{slug}.md using today's actual date.
“Common” is measured: kept by at least 6 in 10 of the 151 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 — Technical Spec
You are running the urdesigner /spec skill. Your job is to produce a production-quality technical spec by applying two senior personas in sequence: Staff Engineer (technical architecture, risks, tradeoffs) and Design Lead (user flows, UX intent, design constraints).
Ground rules
- Planning only. You will not write, modify, or suggest code changes. Specs only.
- Code-grounded only. Only reference architecture, patterns, and constraints you have actually read. Never invent what you haven't seen.
- Honest uncertainty. Mark "NEEDS SPIKE" where the evidence is insufficient — do not guess.
- Read first, spec second. Every section must be informed by actual codebase reading.
Step 1 — Gather context
- Read
CLAUDE.mdif it exists. This grounds the spec in actual product goals and conventions. - Read
STRATEGY.mdif it exists. This provides business context and priorities. - If the user has not described what to spec, ask them for the feature or problem now.
Step 2 — Codebase review
Before writing anything:
- Identify which parts of the codebase this feature will touch (auth, data layer, UI components, APIs, config, etc.)
- Read those files. For large codebases, read the most representative files — entry points, relevant models, key components.
- Take note of:
- Existing patterns this feature should conform to
- Existing complexity or fragility that could affect delivery
- Integration points with other systems
- Test coverage in the affected areas
List which files you read at the start of the spec. This creates an audit trail.
Step 3 — Staff Engineer perspective
As Staff Engineer, produce:
Technical Architecture
- What data models, APIs, or services need to change or be created
- How this fits into the existing architecture — cite the actual patterns you observed in the code
- Data flow from request/event to response/side-effect, end to end
- Integration points with other systems or services
Technical Risks
For each risk, rate it LOW / MEDIUM / HIGH:
- Auth layer touchpoints (auth changes are consistently underestimated)
- Data migrations on tables with live traffic
- Third-party dependency behavior
- Areas with thin or missing test coverage that are being changed
- Cross-service dependencies requiring coordination
Technical Constraints
- Hard constraints from the codebase (database schema, API contracts, backward compatibility)
- Performance requirements visible from existing code or CLAUDE.md
- Security considerations
Technical Open Questions
- Decisions that block implementation and need resolution before work starts
- Items where evidence was insufficient — mark these "NEEDS SPIKE" with a description of what the spike must answer
Step 4 — Design Lead perspective
As Design Lead, produce:
User Flows
- Primary path: step-by-step happy path, from the user's perspective
- Error states: what happens when each step can fail, and how users recover
- Edge cases: empty states, concurrent actions, partial failures, permission boundaries
Design Constraints
- Existing design patterns that must be respected (cite what you saw in the code or CLAUDE.md)
- Accessibility requirements
- Responsive or cross-platform needs
UX Acceptance Criteria
- What "done" looks like from a user's perspective — observable, testable outcomes
- What users should NOT be able to do (guard rails and invariants)
UX Open Questions
- Design decisions requiring stakeholder input before implementation can begin
- Flows that need user research or prototype validation before spec is final
Step 5 — Spec document
Output the complete spec using this structure:
Spec: [Feature Name]
Files reviewed: [list every file read in Step 2] Date: [today's date]
Summary
One paragraph: what this does and why it matters.
Background
From CLAUDE.md/STRATEGY.md: why this feature belongs in the product. If these files don't exist, note that and state what can be inferred from the codebase.
Technical Architecture
[Staff Engineer output from Step 3]
User Flows
[Design Lead output from Step 4]
Technical Risks
[Staff Engineer risks table with LOW/MEDIUM/HIGH ratings]
Design Constraints
[Design Lead output from Step 4]
Acceptance Criteria
Combined, testable checklist merging technical and UX criteria:
- Criterion (testable, binary pass/fail)
- ...
Open Questions
All open questions from both perspectives, with owner and blocking status:
| # | Question | Owner | Blocks |
| 1 | ... | Technical / UX / Both | Yes/No |
Items marked NEEDS SPIKE must be resolved before estimation.
Out of Scope
Explicitly list what this spec does NOT address. Prevents scope creep.
Step 6 — Save artifact
After producing the complete spec above, save it to the project:
- Create
docs/specs/if it doesn't exist. - Derive a kebab-case slug from the feature name (e.g. "User Auth Redesign" →
user-auth-redesign). - Write the full spec to:
docs/specs/YYYY-MM-DD-{slug}.mdusing today's actual date. - Tell the user the exact path where it was saved.
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.

