Home/ai-coding-skills
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
41 Commits 1 Branch 0 Tags
f404792927cc8060ddec36abf566b86c44c00600
Commit Graph

3 Commits

Author SHA1 Message Date
Stefano Fiorini f404792927 feat(do-task): add cursor variant SKILL.md + template (M4) 
Ports the claude-code canonical to Cursor Agent CLI conventions:
- Workspace skill discovery (.cursor/skills/ repo-local preferred,
  ~/.cursor/skills/ global fallback) replaces Skill-tool invocations.
- Helper path resolution prefers .cursor/skills/reviewer-runtime/
  over ~/.cursor/skills/reviewer-runtime/.
- jq added as a hard prerequisite; cursor-agent --version check added.
- Plan-mode guard removed (Cursor has no plan-mode concept).
- Reviewer invocations mandated to --mode=ask --trust
  --output-format json; explicit ban on --mode=agent and --force.
- Added Required Skill Invocation Rules, Variant Hardening Notes
  — Cursor, Common Mistakes, and Red Flags sections.
- Template runtime field = cursor; guardrail line updated.

Core-section schema identical to claude-code canonical.

Reviewer: codex / gpt-5.4. Approved round 1 (0 P0/P1/P2/P3).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-22 14:24:53 -05:00
Stefano Fiorini d69da3a4a8 feat(do-task): add codex variant SKILL.md + template (M3) 
Ports the claude-code canonical to Codex conventions:
- Native skill discovery from ~/.agents/skills/superpowers/<skill>/
  replaces Skill-tool invocations.
- update_plan todos replace Task subagents.
- Helper paths swapped to ~/.codex/skills/reviewer-runtime/.
- Plan-mode guard removed (Codex has no plan-mode concept).
- Prerequisite Check adds symlink verification
  (~/.agents/skills/superpowers -> ~/.codex/superpowers/skills).
- Added Required Skill Invocation Rules, Variant Hardening Notes
  — Codex, Common Mistakes, and Red Flags sections.
- Template runtime field = codex; guardrail line updated.

Core-section schema identical to claude-code canonical.
Frontmatter parses cleanly. Trigger-phrase audit clean.

Reviewer: codex / gpt-5.4. Approved round 1 (0 P0/P1/P2/P3).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-22 14:19:13 -05:00
Stefano Fiorini 437b2024cd feat(do-task): add claude-code variant SKILL.md + template (M1+M2) 
M1 canonical specs (opencode reviewer research, task-plan template,
Review Loop subroutine, Phase 1-10 prose, secret-scan regex list)
are embedded in the M2 claude-code SKILL.md as the canonical
reference; later variants (M3 codex, M4 cursor, M5 opencode) will
fork from this file.

Reviewer: codex / gpt-5.4. Approved after 3 rounds:
- Round 1: 2 P1 + 3 P2 → REVISE
- Round 2: 1 P2 → REVISE
- Round 3: 0 P0/P1/P2, 1 P3 (non-blocking) → APPROVED

Key design properties:
- Plan-review payload strips Runtime State and Review History to
  prevent reviewer session-ID leakage across rounds.
- Secret-scan step 1a redacts matched text to
  [REDACTED:<pattern-label>:<match-length>-chars] before any user
  surfacing; never echoes raw match content.
- Brainstorming required for any behavior-changing task; auto-skip
  limited to pure-documentation and pure-comment-whitespace-rename.
- Phase 3 reviewer config defaults to codex / gpt-5.4 with
  MAX_ROUNDS=10 when user opts for defaults; explicit interactive
  default also gpt-5.4 for internal consistency.
- Template Metadata records Branch Name and Worktree Path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-22 14:13:25 -05:00