sdlc-artifacts
Skill0 starsChanged 17 days agoMITView on GitHub
Defines where SDLC artifacts live (sdlc/<branch>/spec.md, plan.md, todo.md, review.md), the command coverage checklist, the test evidence log, and the gates a branch must pass before a ready PR. Use whenever running /sdlc:spec, /sdlc:plan, /sdlc:build, /sdlc:test, /sdlc:review, /sdlc:code-simplify or /sdlc:pr, when writing or reading a spec, plan or task list, or when asked whether a branch is ready for review.
1 other project uses a version of this.
Adopted by
Most recently taken up by
- alexderz/agentic-toolboxtheir own version, first seen Oct 17, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- alexderz/agentic-toolbox★ 5same name
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 repository26 other files it gives its agents.
- api-and-interface-designSkill
- browser-testing-with-devtoolsSkill
- ci-cd-and-automationSkill
- code-review-and-qualitySkill
- code-simplificationSkill
- constraint-driven-developmentSkill
- context-engineeringSkill
- debugging-and-error-recoverySkill
- deprecation-and-migrationSkill
- documentation-and-adrsSkill
- doubt-driven-developmentSkill
- frontend-ui-engineeringSkill
- git-workflow-and-versioningSkill
- idea-refineSkill
- incremental-implementationSkill
- interview-meSkill
- observability-and-instrumentationSkill
- open-pull-requestSkill
- performance-optimizationSkill
- planning-and-task-breakdownSkill
- security-and-hardeningSkill
- shipping-and-launchSkill
- source-driven-developmentSkill
- spec-driven-developmentSkill
- test-driven-developmentSkill
- using-agent-skillsSkill
The file
We split this skill into the rules it gives an agent
1 rule. About 0 are common, 0 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈0
Distinctive · estimate
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
- Very specific: line 26
Never write SPEC.md, tasks/plan.md or tasks/todo.md at the repo root.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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
SDLC artifacts and gates
The loop is /sdlc:spec → /sdlc:plan → /sdlc:build → /sdlc:test → /sdlc:review → /sdlc:code-simplify → /sdlc:pr. Every
command leaves evidence in the repo, so the next session, the reviewer and /sdlc:pr can see
what actually happened. Chat history is not evidence.
Where artifacts live
Resolve the folder at the start of every command:
BRANCH=$(git rev-parse --abbrev-ref HEAD)
DEFAULT=$(git symbolic-ref --quiet --short refs/remotes/origin/HEAD 2>/dev/null | sed 's#^origin/##')
DIR="sdlc/$BRANCH"- On the default branch (
$DEFAULT, ormain/masterwhen there is no remote) or a detached HEAD: stop. Ask the user to create a feature branch first (git checkout -b feat/<name>). Artifacts on a shared branch collide. - A branch name with
/becomes nested folders (sdlc/feat/percentages/). That's expected. - Never write
SPEC.md,tasks/plan.mdortasks/todo.mdat the repo root. In this kit those are always$DIR/spec.md,$DIR/plan.mdand$DIR/todo.md.
| File | Written by | Holds |
spec.md | /sdlc:spec | Status, objective, scope and non-goals, success criteria, edge-case decisions, open questions |
plan.md | /sdlc:plan, then updated by every command | Approach, tasks with acceptance criteria, risks, command coverage, test evidence |
todo.md | /sdlc:plan, ticked by /sdlc:build | One checkbox per task, same numbering as plan.md |
review.md | /sdlc:review | Findings and what happened to each |
pr.md | /sdlc:pr, only when no PR can be opened | Title, base branch, body, gate results |
A decision with a real trade-off goes in docs/decisions/NNNN-<title>.md as an ADR, linked
from spec.md or plan.md (see sdlc:documentation-and-adrs).
Templates for the three main files are in templates/ next to this skill.
Committing artifacts
Artifacts are committed, so the history shows the loop ran in order and the PR carries them:
/sdlc:speccommitsspec.mdonce it's approved:docs(sdlc): spec for <feature>./sdlc:plancommitsplan.mdandtodo.mdonce the plan is approved:docs(sdlc): plan for <feature>./sdlc:build,/sdlc:test,/sdlc:reviewand/sdlc:code-simplifyinclude the artifact lines they changed (todo.md, coverage, test evidence,review.md) in the same commit as the code they belong to.
Stage files by name. Never git add -A.
The spec status line
spec.md starts with:
# Spec: <feature>
Status: Draft/sdlc:spec changes it to Status: Approved (YYYY-MM-DD) only after the user explicitly says
yes. Downstream commands warn when the spec is still a draft.
Command coverage
plan.md carries this section. Each command ticks its own line when it finishes, with a
short note. Skipping a step is allowed when it's a conscious choice: write
skipped: <reason> instead of a tick.
## SDLC command coverage
- [x] /sdlc:spec: approved 2026-10-06 after 6 questions
- [x] /sdlc:plan: 3 tasks
- [ ] /sdlc:build
- [ ] /sdlc:test
- [ ] /sdlc:review
- [ ] /sdlc:code-simplifyA tick is a claim. Only tick a line after that command actually ran on this branch.
Test evidence
plan.md also carries an append-only log. Record the exact command and its result, never a
summary from memory:
## Test evidence
- 2026-10-06 14:02 · task 2 RED · `pytest tests/test_core.py -q` → 1 failed (expected)
- 2026-10-06 14:05 · task 2 GREEN · `pytest -q && ruff check .` → 14 passed, lint cleanA red-then-green pair is the strongest evidence a test tests something.
Gates
A PR is ready only when every gate passes. /sdlc:pr checks them. Any command may report them.
| Gate | Passes when |
| G1 Spec | spec.md exists, is specific to this feature (no template text left), and is Approved |
| G2 Plan | plan.md has tasks with acceptance criteria, plus the coverage and evidence sections |
| G3 Tasks | every box in todo.md is ticked, or marked skipped: <reason> |
| G4 Evidence | the full test suite and linters pass now, after the last code change, and that run is in Test evidence |
| G5 Alignment | every success criterion in spec.md maps to code and a test, and nothing outside the spec's scope changed |
| G6 Coverage | every coverage line is ticked or explicitly skipped |
Report gates as a table: gate, pass or fail, and the evidence (a file:line or the command
output). Evidence over confidence: "should pass" is a fail.
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.