OpeItcLoc03/claude-skills
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

meta(tasks): pause [active-platform-eval] after design + pre-flight

Browse Source 
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:
vitya
2026-05-05 22:35:55 +03:00
parent 6e4f3f481b
commit d9728ef2e7
5 changed files with 184 additions and 18 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
.tasks/STATUS.md
View File

@@ -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
---