spec
Skill0 starsChanged 10 days agoMITView on GitHub
Write a design spec at docs/specs/<slug>.md, then stop for approval. Refuses trivial work. Use before a feature, redesign, or change touching more than one subsystem.
168 other projects use a version of this.
Adopted by
Most recently taken up by
- thistleknot/skillstheir own version, first seen Nov 8, 2026
- varelaia/claude-skills-publictheir own version, first seen Nov 8, 2026
- mrlemoos/galiciatheir own version, first seen Nov 8, 2026
- PeanutGT/NutsSkillstheir own version, first seen Nov 8, 2026
- standardagents/skillstheir own version, first seen Nov 8, 2026
- Surething-io/cockpittheir own version, first seen Nov 8, 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 versions168 projects use a version of this.
Word for word · 1
- serhiileniv/skills★ 0100% same
Edited · 0
None found.
Wrote their own version · 167
- garrytan/gstack★ 141ksame name
- getsentry/sentry-react-native★ 1.8ksame name
- JuliusBrussee/cavekit★ 1.1ksame name
- kdlbs/kandev★ 1.1ksame name
- getsentry/sentry-dart★ 878same name
- poshan0126/dotclaude★ 871same name
- codewithmukesh/dotnet-claude-kit★ 808same name
- SparkDevNetwork/Rock★ 701same name
- hyperlink-academy/leaflet★ 527same name
- strands-agents/box★ 503same name
157 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
8 rules. 0 are common, 7 are distinctive, and 1 is very specific to this project.
0
Common
Most of the 144 edited versions we read keep these.
7
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 16
Write a spec when the change touches more than one subsystem, adds a dependency or a public contract, or has a real design choice in it.
- Distinctive: line 27
If nothing similar exists, say that explicitly.
- Distinctive: line 31
Create the directory if missing.
- Distinctive: line 59
Before showing it, cut the draft to the Writing rules at the end of this file.
- Distinctive: line 65
Do not write code until the user approves.
- Distinctive: line 73
when the design changes mid-implementation, update the spec in the same commit
- Very specific: line 74
keep it after shipping — docs/ stays the user-facing doc, docs/specs/ is the record
- Distinctive: line 84
Write the report when the spec is approved or abandoned, not at the gate.
“Common” is measured: kept by at least 6 in 10 of the 144 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
/ccs:spec
Non-trivial work starts with a spec, not code. This writes it, shows it, and stops.
Step 0 — refuse trivial work
A typo, a one-line bug, an obvious test does not get a spec. Say so in one line and stop. Ceremony scales to blast radius.
Write a spec when the change touches more than one subsystem, adds a dependency or a public contract, or has a real design choice in it.
Step 1 — read before writing
Ground the spec in what exists. Never describe the current state from memory:
- the files the change would touch, and the conventions already in them
- prior specs in
docs/specs/ - what the repo already does that this would duplicate
If nothing similar exists, say that explicitly. Do not invent a pattern to mirror.
Step 2 — write docs/specs/<slug>.md
Create the directory if missing. Slug: lowercase, hyphens, no dates.
# Spec: <title>
## Goal
What this is for, in two or three sentences. Not a feature list.
## Non-goals
What this deliberately does not do, each with the reason it was excluded.
## Current state
What exists today, with file paths. Facts read from the repo, not recollection.
## Proposed design
Concrete. Layouts, formats, APIs, invariants, command tables, file trees.
A reader must be able to build from this without asking what you meant.
## Acceptance criteria
- [ ] Checkable statements. Each one either passes or fails.
## Open questions
Numbered. Only what the spec genuinely cannot settle — not questions you could
answer by reading the code.Step 3 — KISS the whole thing
Before showing it, cut the draft to the Writing rules at the end of this file.
Step 4 — gate
Report the path. State the open questions as questions. Then stop.
Do not write code until the user approves. "modify: …" means revise the spec and gate again.
After approval
The spec is the design record, not scaffolding:
- implement it with
/ccs:implement docs/specs/<slug>.md - when the design changes mid-implementation, update the spec in the same commit
- keep it after shipping —
docs/stays the user-facing doc,docs/specs/is the record
Writing
One line where one line does. Answer first. State the fact, not the story behind it — no narrating what was tried, no paragraph restating the line above. Two things always stay: why a non-obvious decision was made, and what a check cannot do. Caveats and risks still get said, one line each.
Outcome: success = approved · partial = approved after modify: rounds · failed = abandoned.
Write the report when the spec is approved or abandoned, not at the gate.
Report
Last step, every run, whatever the outcome: write .ccs/reports/<skill>/<YYYY-MM-DD>-<slug>.md
at the repo root, and add .ccs/ to .git/info/exclude if missing. One line per field,
no secrets, tokens or customer data. Print the path.
---
skill: <skill>
date: <YYYY-MM-DD>
repo: <owner/name>
target: <argument, one line>
outcome: success | partial | failed
learned: false
---
Used: <tools, CLIs, MCPs, files that did the work>
Found: <the result, one or two lines>
Friction: <what slowed or blocked it; a user correction; "none">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.

