feedback
Process developer's inline annotations in the plan document and update accordingly without implementing
Skill by tai2
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/tai2-feedback
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: documents
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/feedback
Tools it pre-approves 6
From allowed-tools in SKILL.md: the agent may use these without asking you each time.
Read,Glob,Grep,Edit,Bash(gitrev-parse:*)
What's inside
- Skill name
feedback- Description
- Process developer's inline annotations in the plan document and update accordingly without implementing
- License
- MIT
- Allowed tools
- Read,, Glob,, Grep,, Edit,, Bash(git, rev-parse:*)
- Instructions
- 17 lines in SKILL.md · view on GitHub
Before installing
- Pre-approves some shell commands
Files (1)
- SKILL.md
SKILL.md (first lines)
The project root is: !`git rev-parse --show-toplevel` Read the `plan.md` at the project root. Look for inline annotations/notes the developer has added. These may be marked with comments, notes, or simply new text inserted into the plan — typically quoted strings like "note text here" that stand out from the surrounding plan content. Address every single note: - If a note says to remove a section, remove it - If a note corrects an assumption, fix the assumption throughout the plan - If a note adds a constraint, restructure the relevant sections accordingly After processing all notes, clean up the document so it reads as a cohesive plan without leftover annotation artifacts. **Critical: Do not implement anything. Only update the plan document.**
From tai2/research-plan-feedback-plugin, MIT.
More from tai2/research-plan-feedback-plugin
- 0.518score
plan
tai2
Write a detailed implementation plan document in plans/ based on the actual codebase
SkillBFreshness: BClaude Code +9 - 0.518score
research
tai2
Deep-read a folder, module, or system and write a detailed report to research.md
SkillBFreshness: BClaude Code +9 - 0.513score
add-todos
tai2
Add a detailed todo checklist to the current plan with all phases and individual tasks
SkillBFreshness: BClaude Code +9 - 0.513score
implement
tai2
Execute an approved plan, marking tasks complete as each is finished
SkillBFreshness: BClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 24, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from tai2
- 0.518score
plan
tai2
Write a detailed implementation plan document in plans/ based on the actual codebase
SkillBFreshness: BClaude Code +9 - 0.518score
research
tai2
Deep-read a folder, module, or system and write a detailed report to research.md
SkillBFreshness: BClaude Code +9 - 0.513score
add-todos
tai2
Add a detailed todo checklist to the current plan with all phases and individual tasks
SkillBFreshness: BClaude Code +9 - 0.513score
implement
tai2
Execute an approved plan, marking tasks complete as each is finished
SkillBFreshness: BClaude Code +9
Cite this page
feedback skill. Agent Mart. https://agentmart.dev/skills/tai2-feedback (last updated 2026-10-24)