Files
claude-skills/.wiki/index.md
vitya 8b22d16c20 fix(delegate-task): literal negative-clause kills self-task FP (0.2.0->0.2.1)
«создать задачу себе» false-positive-fired delegate-task instead of
using-tasks (5/5 trials, found by delegate-task-test-trigger). Root cause:
the self-task phrase shares the stem «создать задачу» with the positive
trigger «создать задачу на агента», and the abstract "Does NOT apply when
doing the work yourself" carve-out cannot beat a literal stem-match under
the using-superpowers 1%-rule.

Fix: make the negative literal + routed. Description now lists
«создать задачу себе» / «task for myself» / «поставить себе задачу»
-> using-tasks; body "Ne primenyaetsya" gains a self-assigned bullet plus a
disambiguator («на агента»/«агенту»/«в проект X» = delegate; «себе» = own
board). PATCH bump 0.2.0 -> 0.2.1.

Verification (fresh-context subagents, simulated available-skills registry,
no hint): positives 5/5 -> delegate-task (no regression); negative
«создать задачу себе на завтра» 4/5 -> using-tasks (was 0/5). The 1
residual miss reasoned correctly but tripped on an eval-harness artifact
(prompt forced skill-name-before-reasoning), not description ambiguity.

Wiki: concept page delegate-task-negative-trigger-fp.md + index/log.
Board: [delegate-task-description-fp-fix] -> done.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-09 12:42:44 +03:00

5.9 KiB

Wiki Index

Catalog of all wiki pages. One line per page, organized by type. Updated on every ingest / new page.

Overview

  • overview.md — what claude-skills is, layout, how to navigate

Entities

Concepts

  • active-platform-decision.md — why active-platform is a skill (not a memory entry); why default = Windows; how it's wired into project-bootstrap
  • bootstrap-claude-md-merge.md — project-bootstrap@1.3.0 — Step 5 upgrade path becomes idempotent merge (read → diff vs template → confirm → append missing); fixes silent gap where pre-1.2.0 projects never picked up new canonical triggers (check across all projects, we're on Windows)
  • bootstrap-skill-deps-check.md — project-bootstrap@1.7.0 — Step 5.6 collapses the per-skill "detect-and-recommend" mirror shape into one generic trigger → fulfiller table walker (skill vs plugin kind, never auto-install); subsumes the deferred [bootstrap-recommend-projects-meta] and the existing superpowers-only detector
  • bootstrap-manifest.md — record of which project-bootstrap / setup-wiki / setup-tasks versions initialized this project's .wiki/ and .tasks/ layout (overwritten on re-bootstrap; history in git)
  • build-notes.md — why build.ps1 exists alongside build.sh; PS 5.1 backslash-in-zip gotcha; how to extract a .skill
  • install-cross-platform.md — paired-script parity contract for install.{ps1,sh} AND build.{ps1,sh}; rationale for the --prune / -Prune flag (combined-with-action, global-scan, default-off); install-side prunes target dirs, build-side prunes dist/*.skill files
  • install-portability.mdinstall.sh / build.sh rewritten to drop mapfile (bash 4+) and find -printf (GNU only) so stock macOS (bash 3.2 + BSD find) works
  • context7-setup.md — switched context7 from manual MCP entries to the official plugin; API key in .mcp.json as --api-key; now also captured as setup-context7 skill (one-time install/migrate flow with key discovery)
  • projects-meta-skills.mdsetup-projects-meta + using-projects-meta skill pair for the local projects-meta-mcp stdio server (cross-project tasks + shared Gitea wiki); local-first rule + two-step mutation pattern
  • project-discipline-design.md — design for project-discipline (four cross-project rules: conventions-over-defaults, master-only, semver-bumping, ask-before-push)
  • pulling-before-work-design.md — design for the pulling-before-work skill (mode-3 + skip-on-dirty)
  • repo-layout.md — flat skills/, committed dist/, bash + PowerShell scripts; install model
  • skill-versioning.md — why infra skills carry version: <semver> in frontmatter and how project-bootstrap records them in a per-project manifest
  • skill-vs-plugin.md — when a bare SKILL.md is enough vs when you actually need a plugin (slash commands, hooks, sub-agents, MCP servers); concrete breakdown of superpowers
  • wiki-realignment.md — fixing project-bootstrap to create the Karpathy-canonical wiki layout
  • interns-design — interns-design
  • compress-dedup.mdskills/compress/ deleted as a byte-identical dupe of skills/caveman-compress/; canonical kept for README + SECURITY + caveman-toolkit branding; better Process-step wording ported across; version: 1.0.0 added to caveman-compress frontmatter
  • active-platform-eval-design.md — spec for eval-driven tuning of active-platform: combine the two tasks into one workstream, 20-query cross-platform eval set (≥3 per OS + near-miss negatives), run_loop.py autoloop in parallel with manual body sweep (WSL / BSD / ambiguity), version 1.0.0 → 1.1.0 (MINOR). Status: paused after design + pre-flight check, before eval-set authorship
  • interns-repo-read-design — interns-repo-read-design
  • hermes-skills-rollout-design — hermes-skills-rollout-design
  • tdd-criteria-design — tdd-criteria-design
  • project-bootstrap-meta-isolation.mdproject-bootstrap@1.11.0 — Step 1 ships meta-isolation block in .gitignore (!.claude/, !.tasks/, !.wiki/, ...) so own greenfield/upgrade projects re-enable agent meta-paths against global core.excludesFile cutter. Marker-based append-only on existing files; smoke-tested with negative control
  • interns-grep-audit-design — interns-grep-audit-design
  • session-handoff-skill-design.md — design rationale for the session-handoff skill (sliding overwrite into .tasks/NEXT_SESSION.md, phrase whitelist + substantive-commit heuristic, optional PostToolUse hook for harness-side determinism, orient+ask default, project scope, cluster 7/7 closure)
  • delegate-task-negative-trigger-fp.mddelegate-task v0.2.1 FP fix: «создать задачу себе» stem-matched the «создать задачу на агента» positive trigger; abstract "does NOT apply when doing the work yourself" carve-out loses to literal stem-match under the 1%-rule → made the negative literal + routed (→ using-tasks). Verified pos 5/5, neg 4/5 (was 0/5)

Packages

Sources