Home/ai-coding-skills
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
43 Commits 1 Branch 0 Tags
9853d4937b70ef4f4f96134c7c8983e96a384f3a
Commit Graph

43 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Stefano Fiorini 9853d4937b docs(do-task): add DO-TASK.md + README updates (M6) 
docs/DO-TASK.md covers:
- Purpose, Requirements (variant-specific prereqs + dependency-
  missing messages per variant), Reviewer CLI Requirements table
  (4 CLIs including opencode with fresh-call default).
- Install (4 subsections: Codex, Claude Code, OpenCode, Cursor).
- Per-variant Verify Installation subsections checking CLI binary,
  SKILL.md, run-review.sh, notify-telegram.sh, Superpowers
  sub-skills, and variant extras (Codex symlink, Cursor jq,
  OpenCode Superpowers ls, Cursor repo-vs-global lookup).
- Key Behavior, Dual Review Loops, Subroutine Steps, Reviewer Output
  Contract, Runtime Artifacts, Persistent Artifact Status enum
  (10 values), Failure Handling.
- Secret Scan (subroutine step 1a; per-payload; no caching) with
  canonical 10-pattern regex list and redaction contract.
- Supported Reviewer CLIs table (4 rows, including opencode).
- Notifications, Template Guardrails (14 core sections + Runtime
  State keys), Variant Hardening Notes (4 subsections), Execution
  Workflow Rules.

docs/README.md adds DO-TASK.md entry.

README.md:
- Skills table adds 4 do-task rows (codex, claude-code, opencode,
  cursor).
- Docs links add "Do-task guide" entry.
- Repository Layout adds do-task/ subdirectory.

Reviewer: codex / gpt-5.4. Approved round 2:
- Round 1: 2 P2 (prereqs inaccurate, Verify Installation incomplete)
  + 1 P3 -> REVISE.
- Round 2: 0 P0/P1/P2/P3 -> APPROVED.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
 2026-04-22 14:40:49 -05:00
Stefano Fiorini f5161f584d feat(do-task): add opencode variant SKILL.md + template (M5) 
Ports the claude-code canonical to OpenCode conventions:
- Phase 1 adds Bootstrap Superpowers Context step — uses OpenCode's
  native skill tool to list + verify superpowers/brainstorming,
  superpowers/test-driven-development,
  superpowers/verification-before-completion, and
  superpowers/finishing-a-development-branch before any other phase.
- All sub-skill invocations swapped to OpenCode native skill tool
  with superpowers/<skill> (slash) path format.
- Helper paths swapped to ~/.config/opencode/skills/reviewer-runtime/
  and ~/.config/opencode/skills/do-task/templates/.
- Plan-mode guard removed (OpenCode has no plan-mode concept).
- Prerequisite Check adds opencode --version + Superpowers symlink
  at ~/.config/opencode/skills/superpowers verification.
- Opencode reviewer branch (from M1 research) uses
  `opencode run -m <provider>/<model> --agent plan --format json`
  with fresh-call default and documented opt-in -s <id> resume path.
- Added Required Skill Invocation Rules, Variant Hardening Notes
  — OpenCode, Common Mistakes, and Red Flags sections.
- Template runtime field = opencode; guardrail line updated.

Core-section schema identical across all 4 variants (14 sections).

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 14:30:25 -05:00
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
Stefano Fiorini c344e96984 Remove external web automation provenance refs 2026-04-09 11:11:40 -05:00
Stefano Fiorini 879cccf383 Refine web automation provenance exclusions 2026-04-09 10:31:41 -05:00
Stefano Fiorini c97b7d44e5 feat(web-automation): implement milestone M2 mirror and docs 2026-04-09 10:21:21 -05:00
Stefano Fiorini 99fe6eab4e feat(web-automation): implement milestone M1 canonical codex migration 2026-04-09 10:13:25 -05:00
Stefano Fiorini e917387d4f Force sending Telegram notification upon stopping for user input 2026-03-25 11:59:10 -05:00
Stefano Fiorini 63a048a26c Align reviewer runtime and Telegram notifications 2026-03-24 11:45:58 -05:00
Stefano Fiorini 4d37674626 fix: isolate claude reviewer templates 2026-03-08 18:04:07 -05:00
Stefano Fiorini d44a2288b4 Update Atlassian skill prereq checks 2026-03-06 08:23:49 -06:00
Stefano Fiorini 783bcfa037 fix(atlassian): tighten health checks and review coverage 2026-03-06 07:06:38 -06:00
Stefano Fiorini c3afee091b feat(atlassian): implement milestone M4 - packaging and doc sync 2026-03-06 00:58:23 -06:00
Stefano Fiorini 972789c240 feat(atlassian): implement milestone M3 - confluence and safety controls 2026-03-06 00:53:13 -06:00
Stefano Fiorini 73c4bff901 feat(atlassian): implement milestone M2 - jira command surface 2026-03-06 00:39:54 -06:00
Stefano Fiorini e56f0c9941 feat(atlassian): implement milestone M1 - scaffold skill and shared runtime 2026-03-06 00:23:21 -06:00
Stefano Fiorini 30fb7fa7f0 chore(gitignore): ignore .worktrees local worktrees 2026-03-06 00:09:41 -06:00
Stefano Fiorini 253a4f31e2 feat(implement-plan): route milestone review through shared runtime 2026-03-05 23:23:42 -06:00
Stefano Fiorini c2d47487e0 fix(create-plan): clarify reviewer extraction order 2026-03-05 23:11:43 -06:00
Stefano Fiorini 04bf34544b feat(create-plan): route review through shared runtime 2026-03-05 23:07:43 -06:00
Stefano Fiorini 41a3b9d1ee fix(reviewer-runtime): cover timeout and exit semantics 2026-03-05 22:59:23 -06:00
Stefano Fiorini 8720691135 feat(reviewer-runtime): add shared review supervisor 2026-03-05 22:54:50 -06:00
Stefano Fiorini 526101fd23 chore(gitignore): ignore ai_plan local planning artifacts 2026-03-05 22:19:50 -06:00
Stefano Fiorini d5232c1480 fix(cursor): correct superpowers skill paths to include /skills/ subdirectory 
Superpowers is cloned from git, so skills live under
.cursor/skills/superpowers/skills/<name>/SKILL.md, not
.cursor/skills/superpowers/<name>/SKILL.md.
 2026-03-05 12:28:35 -06:00
Stefano Fiorini 7352e6a9f7 fix(cursor): update skill paths from .cursor/rules/ to .cursor/skills/ 
The Cursor Agent CLI now discovers skills from .cursor/skills/ instead
of the old .cursor/rules/ directory. Update all references across
create-plan and implement-plan Cursor variants and docs.
 2026-03-05 12:04:09 -06:00
Stefano Fiorini 262aed2950 feat(implement-plan): add worktree-isolated plan execution skill (4 variants) 
New skill that executes create-plan artifacts in an isolated git worktree
with iterative cross-model milestone review. Supports codex, claude-code,
opencode, and cursor agent variants.
 2026-03-04 18:02:41 -06:00
Stefano Fiorini d2970b06bd feat(create-plan): add iterative cross-model plan review and Cursor variant 
Add a configurable reviewer phase to all create-plan variants (claude-code,
codex, opencode) that sends the plan to a second CLI/model for iterative
feedback (max 5 rounds). Supported reviewer CLIs: codex, claude, cursor.

Add new Cursor Agent CLI variant with full skill, templates, and
workspace-discovery-based prerequisites (.cursor/rules/).

Update README and docs/CREATE-PLAN.md with Cursor install/verify,
reviewer CLI requirements, and supported reviewer CLIs table.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
 2026-03-04 13:58:11 -06:00
luke 76fd7f374f feat(create-plan/codex): switch to native superpowers workflow and add guardrails 2026-02-11 18:03:16 +00:00
luke 39d758298b docs(web-automation): normalize OpenCode paths to ~/.config/opencode 2026-02-11 17:59:22 +00:00
luke 492732955c docs(create-plan): normalize OpenCode paths to ~/.config/opencode 2026-02-11 17:58:39 +00:00
luke d866b38f18 Harden OpenCode create-plan using native superpowers skill-tool flow 2026-02-09 16:16:54 +00:00
luke efb1a80aac Harden Claude create-plan with explicit sub-skill and plan-mode guards 2026-02-09 16:13:47 +00:00
luke 2988d8fb27 Make Codex create-plan use explicit superpowers commands 2026-02-09 15:36:26 +00:00
luke 0418fe47fa Move install instructions into per-skill docs and remove single INSTALL doc 2026-02-09 05:08:56 +00:00
luke 9ddc17b228 Add docs index and per-skill docs, link from main README 2026-02-09 05:06:13 +00:00
luke 1ba911c3fb Switch create-plan artifacts to ai_plan and enforce gitignore commit 2026-02-09 05:01:28 +00:00
luke aa8a31246a Rename install doc to INSTALL and add full dependency checks 2026-02-09 04:48:44 +00:00
luke 53b05f263b Add Playwright+Camoufox prerequisite checks to web-automation skill docs 2026-02-09 04:43:09 +00:00
luke 4c60c00391 Add web-automation skill variants and inline prerequisite checks 2026-02-09 04:40:04 +00:00
luke 0833934dd5 Add installable create-plan skills for codex, claude-code, and opencode 2026-02-09 04:40:03 +00:00
luke 2d50d677cc Initial commit 2026-02-09 03:30:55 +00:00