iter cadence.4-fix: address quality-review importants + German-loanword sweep (English-only in-tree)

This commit is contained in:
2026-05-11 14:07:44 +02:00
parent 85919e6015
commit 7505af04a1
4 changed files with 14 additions and 14 deletions
@@ -4,7 +4,7 @@
>
> **For agentic workers:** REQUIRED SUB-SKILL: use `skills/implement` to run this plan. Steps use `- [ ]` checkboxes for tracking.
**Goal:** Move docwriter into its own Boss-dispatched skill; shrink audit to architect+bencher; sharpen fieldtest framing as Boss-dispatched post-audit Praxistest; refresh `skills/README.md` cadence taxonomy.
**Goal:** Move docwriter into its own Boss-dispatched skill; shrink audit to architect+bencher; sharpen fieldtest framing as Boss-dispatched post-audit field test; refresh `skills/README.md` cadence taxonomy.
**Architecture:** Pure config/docs reshuffle, no code. Three Boss-orchestrated buckets: per-milestone-mandatory (audit), Boss-judgment post-audit (fieldtest), Boss-judgment post-fieldtest (docwriter). The sequence forms `audit → (Boss: ready?) → fieldtest → (Boss: stable?) → docwriter`.
@@ -117,9 +117,9 @@ git commit -m "iter cadence.2: skills/audit — drop docwriter step (now own ski
**Files:**
- Modify: `skills/fieldtest/SKILL.md`
- [ ] **Step 1: Rewrite the "When to Use / Skipping" trigger section** to frame fieldtest as a Boss-dispatched Praxistest. Replace the current "Triggers:" bullet "A milestone has just closed `audit` cleanly (or with `ratify`-d drift only)." with:
- [ ] **Step 1: Rewrite the "When to Use / Skipping" trigger section** to frame fieldtest as a Boss-dispatched field test. Replace the current "Triggers:" bullet "A milestone has just closed `audit` cleanly (or with `ratify`-d drift only)." with:
> Boss-dispatched after audit closes cleanly, when the orchestrator believes the iteration is correct and wants a Praxistest. The pre-condition is a clean (or `ratify`-d) audit; the trigger is the Boss's judgment-call that the iteration is fertig.
> Boss-dispatched after audit closes cleanly, when the orchestrator believes the iteration is correct and wants a field test. The pre-condition is a clean (or `ratify`-d) audit; the trigger is the Boss's judgment-call that the iteration is complete.
Keep the other two trigger bullets ("A shipped feature is suspected of being LLM-hostile…" / "A user-facing surface change…") — they already match Boss-judgment.
@@ -152,7 +152,7 @@ git commit -m "iter cadence.3: skills/fieldtest — Boss-dispatched framing + or
- Trigger: "API surface stabilized; rustdoc lag suspected"
- Output: "rustdoc updates in `///` and `//!`"
- Mandatory?: "No — Boss-dispatched only"
- fieldtest row description should explicitly say "Boss-dispatched post-audit Praxistest", not "after audit closes".
- fieldtest row description should explicitly say "Boss-dispatched post-audit field test", not "after audit closes".
- Bump the heading from "The six skills" to "The seven skills".
- [ ] **Step 2: Update the pipeline diagram** to reflect the new sequence:
@@ -171,7 +171,7 @@ git commit -m "iter cadence.3: skills/fieldtest — Boss-dispatched framing + or
--(ratify)-> JOURNAL + --update-baseline
--(clean)-+
|
[Boss: iter fertig? if surface-touch:]
[Boss: iter complete? if surface-touch:]
v
fieldtest --(bug)------> debug -> implement (mini)
--(friction)-> brainstorm OR plan (tidy)
@@ -20,7 +20,7 @@ The trio mixes three different cadence-needs:
- **drift** and **regression** are intrinsic to a milestone close —
they compound silently across milestones if deferred, so they
*must* run at every close.
- **fieldtest** measures usability-belief — it's a Praxistest run when
- **fieldtest** measures usability-belief — it's a field test run when
the orchestrator believes the iteration is correct. Findings are
either simple bugs or catastrophic architecture problems; both
decay slowly, so the cadence doesn't have to be per-milestone.
@@ -36,7 +36,7 @@ mandatory pipeline step. This spec splits them.
Three Boss-orchestrated buckets:
1. **Per-milestone, mandatory (audit)**: architect + bencher only.
2. **Boss-judgment, post-audit, "the iter is fertig"**: fieldtest.
2. **Boss-judgment, post-audit, "the iter is complete"**: fieldtest.
3. **Boss-judgment, post-fieldtest, "API surface has settled"**:
docwriter.
@@ -75,7 +75,7 @@ stability windows differ (iter-stable vs. surface-stable).
- `skills/fieldtest/SKILL.md`: trigger section reframes from "after
audit closes cleanly" (which sounded automatic) to "Boss-dispatched
after audit closes cleanly, when the orchestrator believes the
iteration is correct and wants a Praxistest". The pre-condition is
iteration is correct and wants a field test". The pre-condition is
still a clean audit; the trigger is the Boss's judgment-call.
- Add a one-line note on what kind of findings to expect: either
simple bugs (→ debug → implement mini) or catastrophic
+3 -3
View File
@@ -17,9 +17,9 @@ The system was bootstrapped on 2026-05-09. See
| [`brainstorm`](brainstorm/SKILL.md) | New milestone starting | `docs/specs/<milestone>.md` | Hard-gate before plan |
| [`planner`](planner/SKILL.md) | New iteration within an open milestone | `docs/plans/<iteration>.md` | Hard-gate before implement |
| [`implement`](implement/SKILL.md) | Plan exists | Code + tests + per-task commits + per-iter journal entry | Standard iteration path |
| [`audit`](audit/SKILL.md) | Milestone closing OR baseline drift suspected | Architect drift review + three regression scripts | **Mandatory** at milestone close |
| [`audit`](audit/SKILL.md) | Milestone closing OR baseline drift suspected | Drift report + bench-regression report | **Mandatory** at milestone close |
| [`docwriter`](docwriter/SKILL.md) | API surface stabilized; rustdoc lag suspected | rustdoc updates in `///` and `//!` | No — Boss-dispatched only |
| [`fieldtest`](fieldtest/SKILL.md) | Boss-dispatched post-audit Praxistest on a milestone that touched user-visible surface | 2-4 `.ailx` example fixtures + `docs/specs/<date>-fieldtest-<milestone>.md` | Standard milestone-close path; skipped only for purely internal milestones |
| [`fieldtest`](fieldtest/SKILL.md) | Boss-dispatched post-audit field test on a milestone that touched user-visible surface | 2-4 `.ailx` example fixtures + `docs/specs/<date>-fieldtest-<milestone>.md` | No — Boss-dispatched only |
| [`debug`](debug/SKILL.md) | Bug encountered (failing test, segfault, wrong stdout) | RED-test commit + cause analysis | **Mandatory RED-first** for any bug |
## Pipeline
@@ -38,7 +38,7 @@ The system was bootstrapped on 2026-05-09. See
--(ratify)-> JOURNAL + --update-baseline
--(clean)-+
|
[Boss: iter fertig? if surface-touch:]
[Boss: iter complete? if surface-touch:]
v
fieldtest --(bug)------> debug -> implement (mini)
--(friction)-> brainstorm OR plan (tidy)
+3 -3
View File
@@ -1,6 +1,6 @@
---
name: fieldtest
description: Boss-dispatched only, after audit closes clean (or with ratified drift only), when the orchestrator judges the iteration is fertig and wants a Praxistest. Picks 2-4 real-world programming tasks within the milestone's scope, implements each in the AIL Surface form (.ailx — not raw JSON), runs the resulting binaries, and writes a friction-and-bug spec to docs/specs/<date>-fieldtest-<milestone>.md. The spec feeds the next plan as a reference. Implementer simulates a downstream LLM that has only DESIGN.md plus the public examples — never the language's own implementation.
description: Boss-dispatched only, after audit closes clean (or with ratified drift only), when the orchestrator judges the iteration is complete and wants a field test. Picks 2-4 real-world programming tasks within the milestone's scope, implements each in the AIL Surface form (.ailx — not raw JSON), runs the resulting binaries, and writes a friction-and-bug spec to docs/specs/<date>-fieldtest-<milestone>.md. The spec feeds the next plan as a reference. Implementer simulates a downstream LLM that has only DESIGN.md plus the public examples — never the language's own implementation.
---
# fieldtest — LLM-usability field test for a shipped milestone
@@ -35,9 +35,9 @@ rules. This skill file only governs trigger, dispatch, and handoff.
Triggers:
- Boss-dispatched after audit closes cleanly, when the orchestrator
believes the iteration is correct and wants a Praxistest. The
believes the iteration is correct and wants a field test. The
pre-condition is a clean (or `ratify`-d) audit; the trigger is the
Boss's judgment-call that the iteration is fertig.
Boss's judgment-call that the iteration is complete.
- A shipped feature is suspected of being LLM-hostile in some way the
earlier brainstorm could not foresee.
- A user-facing surface change (Decision 6, schema rev, new