meta(tasks): pause [active-platform-eval] after design + pre-flight
Combined the two backlog tasks [active-platform-tuning] + [active-platform-eval] into a single workstream. Eval IS the tuning mechanism; "wait for 5 real signals" was a placeholder replaced by a 20-query synthetic eval set balanced across Win/Lin/Mac. Spec written at .wiki/concepts/active-platform-eval-design.md (~150 lines): 20 queries (>=3 should-trigger per OS + near-miss negatives), run_loop.py 5-iter autoloop in parallel with manual body sweep (WSL clarity, BSD/macOS expansion, ambiguity policy). Workspace at .tasks/active-platform-eval/ (eval-set.json committed, iterations gitignored). Version bump 1.0.0 -> 1.1.0 planned (MINOR). Pre-flight verified: claude CLI on PATH at C:\nvm4w\nodejs\claude.ps1 (Claude Code 2.1.128); run_loop.py present in skill-creator install. Both autoloop deps satisfied -- no fallback to manual single-pass. Per-task file at .tasks/active-platform-eval.md (Goal, Key files, Decisions log, Open questions, Notes). STATUS.md collapsed the two original blocks into one paused block; resume point is Q2 (write 20 queries solo vs run skill-creator HTML-review template). Also fixed in same pause: [install-ps1] STATUS scope expanded to paired install.sh + install.ps1, cross-platform parity, prune flag (lesson from [compress-dedup]). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -1,5 +1,5 @@
|
||||
# Task Board
|
||||
_Updated: 2026-05-05 (compress-dedup done)_
|
||||
_Updated: 2026-05-05 (active-platform-eval paused — design done, awaiting eval-set authorship decision)_
|
||||
|
||||
<!--
|
||||
Canonical layout. One block per task. Per-task deep context lives in
|
||||
@@ -46,10 +46,10 @@ _Updated: 2026-05-05 (compress-dedup done)_
|
||||
|
||||
---
|
||||
|
||||
## ⚪ [install-ps1] — PowerShell-native install.ps1
|
||||
## ⚪ [install-ps1] — paired install.sh + install.ps1 (cross-platform parity, with --prune)
|
||||
**Status:** ready
|
||||
**Where I stopped:** (not started) — `install.sh` already works in git-bash on Windows, so this is convenience for PS-only users
|
||||
**Next action:** mirror `scripts/install.sh` logic in PowerShell (copy `skills/<name>/` → `~/.claude/skills/<name>/`, support `$env:CLAUDE_SKILLS_DIR` override)
|
||||
**Where I stopped:** (not started) — `install.sh` exists, `install.ps1` missing; both must coexist (PS users on Windows shouldn't be forced into git-bash, Linux/Mac users shouldn't be forced into pwsh). Cross-platform = bash + PS *paired*, behaviorally identical.
|
||||
**Next action:** (a) write `scripts/install.ps1` mirroring `install.sh` logic (copy `skills/<name>/` → `~/.claude/skills/<name>/`, support `$env:CLAUDE_SKILLS_DIR` override); (b) add `--prune` flag to **both** scripts that drops `~/.claude/skills/<name>/` for any name not in `skills/<name>/` (lesson from `[compress-dedup]` — manual prune was needed because install.sh can't); (c) confirm `build.ps1`/`build.sh` are already paired (they are) and document the parity invariant in `.wiki/concepts/install-cross-platform.md`. README's install quick-start should show both variants side-by-side per `active-platform` cross-platform-docs convention.
|
||||
**Branch:** (not started)
|
||||
|
||||
---
|
||||
@@ -62,20 +62,11 @@ _Updated: 2026-05-05 (compress-dedup done)_
|
||||
|
||||
---
|
||||
|
||||
## ⚪ [active-platform-tuning] — tune active-platform triggers based on real usage
|
||||
**Status:** ready
|
||||
**Where I stopped:** (not started) — current triggers are best-guess; haven't observed real misfires/missed-fires yet
|
||||
**Next action:** keep a tally of times the skill should have triggered but didn't (or vice versa); revise the description / trigger list after ~5 real signals. Also add WSL handling explicitly if it comes up
|
||||
**Branch:** (not started)
|
||||
|
||||
---
|
||||
|
||||
## ⚪ [active-platform-eval] — run formal skill-creator eval loop on active-platform
|
||||
**Status:** ready
|
||||
**Where I stopped:** (not started) — depends on having ~5 real interactions logged for tuning context
|
||||
**Next action:** invoke `skill-creator` to set up an eval set for `active-platform`; benchmark current vs revised description
|
||||
**Branch:** (not started)
|
||||
**Blocker:** waits on `active-platform-tuning` to gather signals first
|
||||
## 🟡 [active-platform-eval] — eval-driven tuning of active-platform (description + body), absorbs `[active-platform-tuning]`
|
||||
**Status:** paused
|
||||
**Where I stopped:** design doc complete (`.wiki/concepts/active-platform-eval-design.md`, ~150 lines); per-task file complete (`.tasks/active-platform-eval.md`); STATUS.md collapsed the two original ⚪ tasks into this one block. Pre-flight verified: `claude` CLI on PATH at `C:\nvm4w\nodejs\claude.ps1` (Claude Code 2.1.128); `run_loop.py` present at `~/.claude/plugins/cache/claude-plugins-official/skill-creator/unknown/skills/skill-creator/scripts/run_loop.py`. Stopped right before eval-set authoring at user request — paused for asynchronous follow-up. No code touched, no tooling launched, no `.tasks/active-platform-eval/` workspace dir created yet.
|
||||
**Next action:** resume by answering Q2 from the chat ("eval set — write 20 queries solo from current SKILL.md + concept-page open questions, or run skill-creator's HTML review template first for user-driven edits before kickoff?"), then (a) build `.tasks/active-platform-eval/eval-set.json`, (b) snapshot skill to `.tasks/active-platform-eval/skill-snapshot/`, (c) launch run_loop.py in background, (d) parallel manual body sweep, (e) apply changes + bump to 1.1.0 + rebuild + reinstall + final report + commit.
|
||||
**Branch:** master
|
||||
|
||||
---
|
||||
|
||||
|
||||
49
.tasks/active-platform-eval.md
Normal file
49
.tasks/active-platform-eval.md
Normal file
@@ -0,0 +1,49 @@
|
||||
# active-platform-eval
|
||||
|
||||
## Goal
|
||||
Tune `active-platform` (description + body) using skill-creator's `run_loop.py` for description optimization in parallel with a manual body sweep. Replaces the placeholder "5 real signals" approach with a 20-query synthetic eval set balanced across Windows / Linux / macOS. Absorbs the two ⚪ tasks `[active-platform-tuning]` + `[active-platform-eval]` into one workstream — they were inseparable in practice (eval *is* the tuning mechanism). Bumps `version: 1.0.0 → 1.1.0` (MINOR — improved triggering + expanded body coverage; behavior compatible).
|
||||
|
||||
## Key files
|
||||
- `skills/active-platform/SKILL.md` — frontmatter description (run_loop output) + body (manual sweep) + version bump
|
||||
- `dist/active-platform.skill` — rebuild after edits
|
||||
- `~/.claude/skills/active-platform/` — reinstall
|
||||
- `.tasks/active-platform-eval/eval-set.json` — 20-query trigger eval set, committed before kickoff
|
||||
- `.tasks/active-platform-eval/iteration-N/` — workspace for run_loop iterations (gitignored; transient)
|
||||
- `.tasks/active-platform-eval/.gitignore` — scopes the iteration subdirs out of git
|
||||
- `.wiki/concepts/active-platform-eval-design.md` — design doc (this task's spec; already written)
|
||||
- `.wiki/concepts/active-platform-eval.md` — final report (eval set summary, before/after scores, body diff summary)
|
||||
- `.wiki/concepts/active-platform-decision.md` — open-questions list (WSL, macOS coverage) is exactly what this eval resolves; cross-link
|
||||
- `.wiki/index.md` — add new concept entry
|
||||
- `.wiki/log.md` — append decision line
|
||||
- `.tasks/STATUS.md` — collapse `[active-platform-tuning]` + `[active-platform-eval]` ⚪ blocks into one 🔴 active block, then 🟢 done
|
||||
|
||||
## Decisions log
|
||||
- 2026-05-05: combined the two backlog tasks into one. The split was an artefact of the original "wait for production misfires" model; synthetic eval covers the same ground in one pass with controlled cross-platform balance.
|
||||
- 2026-05-05: chose autoloop (`run_loop.py` × 5 iterations) **in parallel with** manual body sweep, per user explicit request ("давай одновременно"). The two halves don't conflict — autoloop only mutates frontmatter description; body sweep only mutates body.
|
||||
- 2026-05-05: model for run_loop = `claude-opus-4-7` (current session model — triggering test must match what the user actually experiences in production).
|
||||
- 2026-05-05: workspace at `.tasks/active-platform-eval/` (project-internal, not `~/AppData/Local/Temp/...`) so the eval set lives in git and the workflow is reproducible from any clone. Iteration subdirs gitignored — transient HTML reports + per-iteration outputs would balloon the repo.
|
||||
- 2026-05-05: eval set composition forced cross-platform balance: ≥3 should-trigger queries per OS (Win/Lin/Mac), rest implicit-shell-context. ≥10 should-not-trigger queries are deliberately near-misses (library API questions, README meta-questions, architecture talk) — only 1 genuinely-unrelated negative as a sanity baseline. Per-question-override cases marked `should_trigger: true` (the skill *should* fire, but body handles no-session-flip behavior, which the eval can't measure directly).
|
||||
- 2026-05-05: spec lives at `.wiki/concepts/active-platform-eval-design.md` per project-discipline Rule 1 (overrides skill-creator's default `docs/superpowers/specs/`). Final report goes to a sibling `active-platform-eval.md` (separate "what we're going to do" vs "what we did").
|
||||
- 2026-05-05: version bump 1.0.0 → 1.1.0 (MINOR) — added capability (better triggering, broader body coverage), no removed coverage, behavior compatible. Recorded in commit message per Rule 3.
|
||||
- 2026-05-05: install-ps1 task scope expanded in the same session (paired install.sh + install.ps1, cross-platform parity, --prune flag) — out of scope here, but logged in STATUS.md so we don't lose the requirement when this task closes.
|
||||
|
||||
## Open questions
|
||||
- [ ] Does the `claude` CLI exist on PATH? `run_loop.py` shells out to `claude -p` for triggering tests. If not on PATH → fall back to manual single-pass description rewrite (still useful, but loses the train/test optimization).
|
||||
- [ ] How does `run_loop.py` behave on Windows? skill-creator's docs assume bash-like shell for the invocation; may need to invoke through git-bash or adjust working-directory handling.
|
||||
- [ ] Per-question override eval cases — confirmed `should_trigger: true` (skill fires) but the no-session-flip behavior is body-driven, not measurable by trigger eval. Document in `.wiki/concepts/active-platform-eval.md` final report so future readers know the eval didn't directly measure that.
|
||||
|
||||
## Completed steps
|
||||
- [x] 2026-05-05: read current `active-platform/SKILL.md` (lines 1-86) and `active-platform-decision.md` (lines 1-46) to baseline scope and known weak spots (WSL, macOS coverage, trigger phrase comprehensiveness).
|
||||
- [x] 2026-05-05: invoked `superpowers:brainstorming` skill, walked through the design choices (combine vs split, autoloop vs manual, parallel vs sequential), reached approval on combined-and-parallel plan.
|
||||
- [x] 2026-05-05: wrote design doc `.wiki/concepts/active-platform-eval-design.md` (per project-discipline Rule 1).
|
||||
- [x] 2026-05-05: pre-flight verified — `claude` CLI on PATH (`C:\nvm4w\nodejs\claude.ps1`, Claude Code 2.1.128); `run_loop.py` present at `~/.claude/plugins/cache/claude-plugins-official/skill-creator/unknown/skills/skill-creator/scripts/run_loop.py`. Both autoloop dependencies satisfied; no fallback to manual single-pass needed.
|
||||
- [x] 2026-05-05: STATUS.md collapsed the two original ⚪ tasks (`[active-platform-tuning]` + `[active-platform-eval]`) into one block, set 🔴 active during design phase, then 🟡 paused at user request before eval-set authorship.
|
||||
- [x] 2026-05-05: paused at user request — task complete through design + tooling pre-flight; resume point is Q2 (write eval set solo vs HTML-review).
|
||||
- (further steps appended during implementation when resumed)
|
||||
|
||||
## Notes
|
||||
- Skill-creator path on this machine: `~/.claude/plugins/cache/claude-plugins-official/skill-creator/unknown/skills/skill-creator/`. `run_loop.py` lives under that at `scripts/run_loop.py`.
|
||||
- Snapshot the current skill before kickoff: `cp -r skills/active-platform .tasks/active-platform-eval/skill-snapshot/` so the run_loop's "old description" baseline matches what we're tuning *from*, regardless of any edits I make to the body during the parallel sweep.
|
||||
- run_loop accepts `--max-iterations N`. Plan = 5 (skill-creator default + sufficient signal for a single description field).
|
||||
- run_loop output: `best_description` selected by held-out test score, not train score (skill-creator's anti-overfit choice). Trust the test-score winner unless qualitative review of the score table reveals an obvious flaw.
|
||||
- After this task: `[install-ps1]` (already updated in STATUS.md to require paired install.sh + install.ps1 + `--prune`), then revisit any further skill backlog items.
|
||||
Reference in New Issue
Block a user