qraspi-implement
Skill3 starsChanged 3 months agoMITView on GitHub
QRASPI Implement phase — grows the green walking skeleton ONE approved slice at a time with strict Red-Green-Refactor per phase, keeping fitness gates green, and writes a per-slice proof log. Use for '/qraspi-implement <project>', 'implement the slice on the skeleton', 'build the approved plan-{slice} with RGR'. Requires plan-{slice}.md status: approved and a green skeleton. Not for a feature in an EXISTING codebase (qrspi-implement), the deprecated RPI workflow, or a bare TDD cycle with no plan (tdd).
In this repository86 other files it gives its agents.
- AGENTS.mdAGENTS.md
- project-templates/AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- project-templates/CLAUDE.mdCLAUDE.md
- alembic-migration-managerSkill
- architecture-journalSkill
- architecture-reviewSkill
- automated-code-reviewSkill
- axum-scaffolderSkill
- capture-consolidateSkill
- cargo-package-scaffoldSkill
- code-review-coachSkill
- confluence-guide-writerSkill
- dependency-mapperSkill
- doc-syncSkill
- dotnet-architecture-checklistSkill
- dotnet-controller-api-scaffolderSkill
- dotnet-security-reviewSkill
- dotnet-vertical-sliceSkill
- ef-migration-managerSkill
- email-captureSkill
- environment-healthSkill
- evaluate-testsSkill
- fastapi-scaffolderSkill
- fitness-functionsSkill
- jira-comment-writerSkill
- legacy-migration-analyzerSkill
- minimal-api-scaffolderSkill
- nuget-package-scaffoldSkill
- oss-vettingSkill
- pattern-tradeoff-analyzerSkill
- php-api-scaffolderSkill
- php-architecture-checklistSkill
- php-feature-sliceSkill
- php-migration-managerSkill
- php-package-scaffoldSkill
- php-security-reviewSkill
- pr-feedback-writerSkill
- pypi-package-scaffoldSkill
- python-architecture-checklistSkill
- python-feature-sliceSkill
- python-modernization-analyzerSkill
- python-security-reviewSkill
- qraspi-architectureSkill
- qraspi-graduateSkill
- qraspi-planSkill
- qraspi-questionsSkill
- qraspi-researchSkill
- qraspi-skeletonSkill
- qrspi-implementSkill
- qrspi-planSkill
- qrspi-questionsSkill
- qrspi-researchSkill
- qrspi-specSkill
- react-app-scaffolderSkill
- react-architecture-checklistSkill
- react-component-scaffolderSkill
- react-feature-sliceSkill
- react-modernization-analyzerSkill
- react-security-reviewSkill
- The first 60 shown.
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 63
Exit criteria: every phase in plan-{slice}.md executed with RED + GREEN proof logged.
≈ “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
QRASPI Implement
"Amateurs practice until they get it right; professionals until they can't get it wrong."
Core Philosophy
The Implement phase grows the walking skeleton one approved slice at a time. Architecture locked
the decisions, Plan made the slice mechanical -- you execute plan-{slice}.md without re-opening
either. Each phase inside the slice plan runs a full Red-Green-Refactor loop, with RED and GREEN
command output captured to the slice's log. The skeleton's fitness gates are live, so GREEN means
tests pass and gates stay green. One slice is ideally one fresh session -- the per-slice log is the
resumption point. You stop the instant the plan does not cover something.
Non-Negotiable Constraints:
- APPROVED-GATED -- never start without
plan-{slice}.mdstatus: approved; never implement from memory - SKELETON GREEN FIRST -- pre-flight requires
skeleton.mdci_green: trueAND a green baseline run (tests + fitness gates); a red baseline is a STOP, not yours to fix - ONE SLICE, PHASES IN ORDER -- execute the phases inside
plan-{slice}.mdin order; never reorder, parallelize, or skip; other backlog slices are out of scope for this run - RGR PER PHASE, GATES STAY GREEN -- RED (test fails) -> GREEN (minimal code, build+test+fitness gates pass) -> REFACTOR (stays green); a tripped gate is fixed, never disabled
- RECORD THE PROOF -- write RED and GREEN command output to
implementation-log-{slice}.md - INVENTION = STOP -- anything not in the plan stops the slice (re-run /qraspi-plan); a design change routes to /qraspi-architecture. Never improvise.
- CONTEXT BUDGET: keep utilization under 40%. At 60% (or end of the slice), checkpoint to the slice log and tell the user to start a fresh session.
Workflow
PRE-FLIGHT
[ ] Locate the project folder thoughts/shared/qraspi/YYYY-MM-DD-{slug}/
[ ] Read skeleton.md: status: complete AND ci_green: true. If not green -> STOP; route to /qraspi-skeleton
[ ] Read plan-{slice}.md for the target slice. If absent -> STOP; route the user to /qraspi-plan
[ ] Confirm plan-{slice}.md status: approved (else STOP, ask the human) and run the baseline suite
(tests + fitness gates). If red -> STOP; report; do not fix it
[ ] Read the ENTIRE plan-{slice}.md; identify the next unfinished phase from implementation-log-{slice}.md
PHASE LOOP (one phase = one vertical increment inside the slice; inner loop delegated to tdd)
1. RED — write the phase's failing test; RUN it; it MUST FAIL. If it passes, fix the test.
2. GREEN — write the minimal production code; RUN build + tests + fitness gates; ALL MUST PASS.
3. REFACTOR — clean up; RUN again; it MUST stay GREEN (tests AND gates).
4. RECORD — append to implementation-log-{slice}.md: RED output, GREEN output, gate result, files changed.
5. CHECKPOINT — suggest a commit; if context > 40% or the slice is done, hand off a fresh session.
REPORT
Phases complete / total · fitness gates green · next backlog slice (/qraspi-plan) or
"all backlog slices built -> /qraspi-graduate".Exit criteria: every phase in plan-{slice}.md executed with RED + GREEN proof logged;
build/tests AND fitness gates GREEN; the user knows the next slice or that the system can graduate.
State Block
<qraspi-implement-state>
phase: PRE-FLIGHT | RED | GREEN | REFACTOR | RECORD | CHECKPOINT | COMPLETE
project_folder: thoughts/shared/qraspi/YYYY-MM-DD-{slug}/
skeleton_ci_green: true | false # MUST be true to proceed
plan_present: true | false # plan-{slice}.md -- MUST be true to proceed
plan_approved: true | false # MUST be true to proceed
baseline_green: true | false # tests + fitness gates -- MUST be true before any change
slice_name: [the slice being built]
current_phase: [NN]
phases_total: [count]
phases_complete: [count]
fitness_gates_green: true | false # MUST stay true -- it is part of GREEN
last_verification: red | green | pending # RED step expects red; GREEN/REFACTOR expect green
context_budget: under-40 | approaching-60 | checkpoint-now
</qraspi-implement-state>Output Template
See references/implementation-log-template.md for the per-slice implementation-log-{slice}.md
structure -- the per-phase RED/GREEN proof, gate result, files changed, and resume note.
Integration with Other Skills
| Skill | Relationship |
qraspi-plan | Prior phase. Its approved plan-{slice}.md is the contract this phase executes. |
qraspi-skeleton | Supplies the green skeleton this phase grows on and the live fitness gates GREEN must keep passing. |
tdd-loop | The inner loop each phase runs -- the test-first mechanics this skill enforces per phase. |
qraspi-graduate | Terminal next step once every backlog slice is built -- hands the repo to QRSPI. |
dotnet-vertical-slice / python-feature-slice / rust-feature-slice | Stack scaffolders for the slice's phases. |
qrspi-implement | Brownfield sibling: same per-slice RGR, on an existing codebase's plan.md. |
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.

