Skip to content

HigorAlves/orc / codex/orc/content/skills/phases

phases

Verified

Per-phase playbooks for orc commands, loaded one phase at a time

FileKindSize
SKILL.mdskill md3.4 KB
references/flow/PHASE-2-RFC.mdmarkdown606 B
references/flow/PHASE-3-PLAN.mdmarkdown1.4 KB
references/flow/PHASE-4-START.mdmarkdown3.0 KB
references/flow/PHASE-5-IMPLEMENT.mdmarkdown6.6 KB
references/flow/PHASE-6-QA.mdmarkdown3.5 KB
references/flow/PHASE-7-SHIP.mdmarkdown3.1 KB
references/flow/PHASE-8-ADDRESS.mdmarkdown921 B
references/flow/PHASE-9-CLEANUP.mdmarkdown1.9 KB
references/plan/DISCOVERY.mdmarkdown871 B
references/plan/PHASE-1-INIT.mdmarkdown2.1 KB
references/plan/PHASE-2-DRAFT.mdmarkdown2.5 KB
references/plan/PHASE-3-GRILL.mdmarkdown333 B
references/plan/PHASE-4-CONFIRM.mdmarkdown1.5 KB
references/plan/PHASE-5-DECOMPOSE.mdmarkdown443 B
references/plan/PRD.mdmarkdown1.1 KB
references/plan/REFACTOR.mdmarkdown1.1 KB
references/qa/PACKET.mdmarkdown2.7 KB
references/qa/PHASE-2-VERIFY.mdmarkdown662 B
references/qa/PHASE-3-REVIEW.mdmarkdown939 B
references/qa/PHASE-4-BROWSER.mdmarkdown915 B
references/qa/PHASE-5-VERDICT.mdmarkdown1.8 KB
references/qa/PHASE-6-PUBLISH.mdmarkdown760 B
references/retro/PHASE-1-SOURCES.mdmarkdown1.2 KB
references/retro/PHASE-2-CANDIDATES.mdmarkdown4.8 KB
references/retro/PHASE-3-PRESENT.mdmarkdown892 B
references/retro/PHASE-4-ACT.mdmarkdown1.2 KB
references/retro/PHASE-5-PROPOSE.mdmarkdown2.1 KB
references/ship/PHASE-1-VERIFY.mdmarkdown733 B
references/ship/PHASE-2-REVIEW.mdmarkdown369 B
references/ship/PHASE-3-COMPOSE.mdmarkdown2.0 KB
references/ship/PHASE-4-GATE.mdmarkdown1.5 KB
references/ship/PHASE-4.5-SIZE-GATE.mdmarkdown2.9 KB
references/ship/PHASE-5-PUSH.mdmarkdown2.9 KB
references/ship/PHASE-6-CLEANUP-HINT.mdmarkdown794 B
references/stack-pr/PHASE-1-TOOLING.mdmarkdown1001 B
references/stack-pr/PHASE-2-PRECONDITIONS.mdmarkdown916 B
references/stack-pr/PHASE-3-ANALYZE.mdmarkdown1.0 KB
references/stack-pr/PHASE-4-PREVIEW.mdmarkdown2.1 KB
references/stack-pr/PHASE-5-EXECUTE.mdmarkdown1.9 KB
references/stack-pr/PHASE-6-WRITEBACK.mdmarkdown1.6 KB
references/stack-pr/PHASE-7-SUMMARY.mdmarkdown681 B
references/stack-pr/SMART.mdmarkdown877 B
references/triage/BRIEFS.mdmarkdown1.8 KB
references/triage/OUT-OF-SCOPE.mdmarkdown1.3 KB
references/triage/PHASE-1-QUEUE.mdmarkdown786 B
references/triage/PHASE-2-ITEM.mdmarkdown2.4 KB
references/triage/PHASE-3-OVERRIDE.mdmarkdown610 B
references/triage/PHASE-4-INTAKE.mdmarkdown2.0 KB
references/triage/ROLES.mdmarkdown1.2 KB
references/triage/VALIDITY.mdmarkdown2.2 KB
references/wayfinder/MAP.mdmarkdown4.6 KB
references/wayfinder/MODE-A-CHART.mdmarkdown2.1 KB
references/wayfinder/MODE-B-WORK.mdmarkdown1.7 KB

references/flow/PHASE-6-QA.md

View on GitHub
<!-- orc-flow/P6 -->
# $orc-flow — Phase 6-QA

_Loaded on demand via orc-phases. Do not run this phase from memory — this file is the phase._


Detect web vs code mode (heuristic on changed files vs main).

**Skip the redundant suite re-run when the evidence is current**: if the ledger shows every slice `committed` AND the digest records `Suite: green @ <sha>` with `<sha>` == current HEAD AND Phase 5 ran sequentially (per-slice suite runs happened on this exact tree), go straight to self-review — the suite verdict is already on record. Re-run `orc-verification-before-completion` (tests + lint + type-check) when any of those fail: sha mismatch, incomplete ledger, or the parallel batch-apply path ran (applied diffs invalidate per-slice evidence). This skip is evidence-keyed, not trust-keyed — one paragraph to revert if recorded evidence ever proves unreliable.

Always invoke `orc-caveman-review` (self-review of diff) — that's a different lens, not re-derivation.

When the diff touches security-sensitive paths (auth, sessions, raw SQL, deserialization, file upload, network egress, dependency surface) — dispatch `orc-security-reviewer` in parallel with the self-review. Merge findings before surfacing.

For web changes, invoke **`orc-browser-qa`** and execute its protocol end-to-end — target resolution (`orc-qa-targets`), env attach/provision for local targets, the driver gate (`--driver`/`--target` or settled decisions skip them), the acceptance-criteria load, then Driver P (Playwright), Driver A validator dispatch or Driver B inline. The skill is the single source of truth shared with `$orc-qa` Phase 4; flow adds only the workspace note: the web-surface repo comes from the plan's "Repo touchpoints" (`repoPath = <workspaceRoot>/<that repo>`), cross-repo integration evidence lands at the workspace-level `qa/` dir, repo-local QA stays per-repo. The environment stays up across the QA-partial → fix → re-run loop; teardown happens in Phase 9.

If verification flags untested branches, dispatch `orc-test-author` to fill them in before continuing.

**No gate on a clean pass.** The verdict is computed from the evidence packet, not vibes — when the verdict is `pass` AND the packet is complete, print the verdict line + artifact list and advance to Phase 7. **Completeness is driver-shaped, read from the packet's `qa-manifest.json`** — every file its `artifacts` names exists on disk, and every `acceptance` row is `pass` or a `skipped` carrying a reason. (a playwright packet has a stitched video + traces, no PNGs) (Do not check for screenshots and a HAR by name: a chrome-driver packet has neither, and hard-coding Driver A's shape here made a clean chrome pass unreachable.) Code mode is unchanged: suite + lint + type-check green.

**Explainer (opt-in, soft-inward, header `Explainer`).** After a clean web-mode pass print `➡️ Explainer available` and `the available user-question tool (or ask in chat)`: **Skip (Recommended)** · **Build now** (invoke `orc-explainer` on the packet, then continue to Phase 7) · **Later** (note `$orc-explain` in the digest). `--explainer` pre-answers Build now; `guided`/`full` pick Skip unless `--explainer`.

Gate only on anomaly (verdict `partial`/`fail`, incomplete evidence, or web QA about to be skipped):

```
the available user-question tool (or ask in chat) (anomalous QA verdict):
- QA partial — let me address findings, then re-run QA
- QA failed — back to implement
- Skip web QA (with rationale, logged) — only when --no-web justified
- Abort
```

slack-gif-creatoranthropics/skillsKnowledge and utilities for creating animated GIFs optimized for Slack. Provides constraints, validation tools, and animation concepts. Use when users request animated GIFs for Slack like "make me a GIF of X doing Y for Slack."Stars: 198kUpdated Claude CodeCodexVerifiedInstall
ponytailDietrichGebert/ponytailLazy senior dev mode for any coding task: the smallest change that fully solves it, and a reply a busy human understands in one read.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailHarvest every shortcut: comment into one debt ledger, so deferrals get tracked instead of forgotten. One-shot report.Stars: 196kUpdated Claude CodeCodexVerifiedInstall
ponytail-debtDietrichGebert/ponytailList every `shortcut:` comment (and older `ponytail:` ones) as a debt ledger. One-shot report, changes nothing. Use for "ponytail debt", "what did ponytail defer", "list the shortcuts", /ponytail-debt.Stars: 196kUpdated Claude CodeCodexVerifiedInstall