feat(sdlc): SDLC phase prompt corpus (#1705)#1814
Draft
tomgreen981111-cipher wants to merge 1 commit into
Draft
Conversation
10 coordinated prompt files in koan/skills/core/sdlc/prompts/ — each with explicit input/output artifact contracts, so phases build on each other rather than running in isolation: - research.md — codebase analysis, risk classification (Low/Medium/High) - architecture.md — reads RESEARCH.md, produces ADR.md with rejected alternatives - planning.md — reads ADR+RESEARCH, produces PLAN.md with machine-runnable acceptance criteria - implementation.md — reads PLAN.md, writes code + records test output in IMPLEMENTATION.md - security_review.md — diff-only, VERDICT: APPROVED/NEEDS_FIX block for fix-loop parsing - qa_review.md — coverage gaps + acceptance criteria check, same verdict format - sre_review.md — resource leaks, failure modes, deployment safety, same verdict format - fix.md — reads only NEEDS_FIX verdicts, touches only cited files, bounded by MAX_FIX_ITERATIONS - tech_writer.md — reads final IMPLEMENTATION.md, writes CHANGELOG + README updates - orchestrator.md — reads STATE.json, queues next phase mission, sends Telegram updates All prompts load via load_skill_prompt() with @include partials resolved. SKILL.md skeleton created (handler.py comes with Anantys-oss#1707). 55 tests verify loading, substitution, and artifact contracts. Closes Anantys-oss#1705
7767cc7 to
deb639b
Compare
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
10 coordinated prompt files for the
/sdlcmulti-phase workflow — the intellectual core of the SDLC initiative.Why
Shipping the orchestrator (#1707) without quality prompts produces a workflow worse than running
/plan+/implement+/reviewmanually. Each phase needs to know its exact input artifacts, output schema, and constraints — so agents build on each other rather than starting from scratch.How
Each prompt in
koan/skills/core/sdlc/prompts/has a rigid contract:research.mdRESEARCH.md(risk: Low/Medium/High)architecture.mdRESEARCH.mdADR.md(chosen approach + rejected alternatives)planning.mdADR.md+RESEARCH.mdPLAN.md(machine-runnable acceptance criteria)implementation.mdPLAN.md+ADR.md+RESEARCH.mdIMPLEMENTATION.md(real test output) + opens draft PRsecurity_review.mdIMPLEMENTATION.mdSECURITY.mdwithVERDICT: APPROVED/NEEDS_FIXqa_review.mdIMPLEMENTATION.mdQA.mdwith same verdict formatsre_review.mdIMPLEMENTATION.mdSRE.mdwith same verdict formatfix.mdNEEDS_FIXverdictstech_writer.mdIMPLEMENTATION.mdorchestrator.mdSTATE.jsonReview prompts are diff-only — they cannot flag pre-existing code. The
VERDICT:format is rigid enough for regex parsing, forgiving enough that agents produce it consistently.SKILL.mdskeleton created withgroup: code,worker: true,github_enabled: true. Thehandler.pyis #1707's responsibility.Testing
55 tests in
koan/tests/test_sdlc_prompts.pyverify:load_skill_prompt(){@include}partials resolve correctly{ISSUE_NAME}and other placeholders are substitutedVERDICT: APPROVEDandVERDICT: NEEDS_FIXexamplesTestCoreSkillGroupEnforcementpassesCloses #1705
Dependencies: #1704 (state layer, open in #1813), needed by #1707 (orchestrator)
Generated by Kōan