revise
Addresses review feedback on an open pull request with loop-spec: turns each review comment into a checked criterion, fixes them on the PR's own branch…
Skill by aztechead
Chalk Labs
Need help deploying revise?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/aztechead-revise
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
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 and code. Checked Nov 2, 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/revise
What's inside
- Skill name
revise- Description
- Addresses review feedback on an open pull request with loop-spec: turns each review comment into a checked criterion, fixes them on the PR's own branch, verifies, and pushes. Use when a person or bot left review comments on a PR to resolve. Not for new work (cycle) or a bug found outside review (debug).
- License
- MIT
- Instructions
- 17 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
Start (or resume) a loop-spec run on the pull request:
"${CLAUDE_SKILL_DIR}/../loop-spec/program/loop-spec" start --pr "{pr}" --request "{instruction}"
- `{pr}`: the PR number or URL. From a workspace root, use the URL when the number
could belong to more than one of its repositories.
- `{instruction}`: anything the user said beyond the PR reference; leave `--request`
out when there is nothing.
- Add `--autonomous` if no one can answer questions during this run (a headless or
unattended run, or arguments that start with `--autonomous`). Add `--supervised` instead
when the arguments start with `--supervised`.
- When the instruction is long or holds quotes, backticks, or `$`, write it to a file
and pass `--request-file <path>` instead of `--request`.
Then follow `${CLAUDE_SKILL_DIR}/../loop-spec/SKILL.md` until the run ends.From aztechead/loop-spec, MIT.
More from aztechead/loop-spec
- 0.570score
loop-spec
aztechead
The loop-spec method for taking a coding request to a verified pull request: a spec with checkable acceptance criteria, a task graph (DAG) built in parallel…
SkillAFreshness: AClaude Code +9 - 0.565score
cycle
aztechead
Takes a feature request or spec file to a verified pull request with loop-spec: spec, task graph, parallel implementation, clean-checkout verify, one PR.
SkillAFreshness: AClaude Code +9 - 0.559score
debug
aztechead
Reproduces and fixes a specific failure with loop-spec: confirms the bug at the start commit, finds the root cause, fixes it with a regression test, and…
SkillAFreshness: AClaude Code +9 - 0.559score
micro
aztechead
Makes a small, well-defined code change (a one-file fix, a rename, a tiny tweak) and lands it as a verified PR in one short loop-spec pass.
SkillAFreshness: AClaude Code +9 - 0.556score
status
aztechead
Shows where loop-spec runs stand in this repository: each run's phase, task graph, verify result, and PR.
SkillAFreshness: AClaude Code +9
Signals
- Stars
- 0
- Forks
- 1
- Open issues
- 0
- Last commit (this folder)
- Oct 5, 2026 (28 days ago)
- Last release
- Oct 21, 2026 (11 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/aztechead/loop-spec
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from aztechead
- 0.570score
loop-spec
aztechead
The loop-spec method for taking a coding request to a verified pull request: a spec with checkable acceptance criteria, a task graph (DAG) built in parallel…
SkillAFreshness: AClaude Code +9 - 0.565score
cycle
aztechead
Takes a feature request or spec file to a verified pull request with loop-spec: spec, task graph, parallel implementation, clean-checkout verify, one PR.
SkillAFreshness: AClaude Code +9 - 0.559score
debug
aztechead
Reproduces and fixes a specific failure with loop-spec: confirms the bug at the start commit, finds the root cause, fixes it with a regression test, and…
SkillAFreshness: AClaude Code +9 - 0.559score
micro
aztechead
Makes a small, well-defined code change (a one-file fix, a rename, a tiny tweak) and lands it as a verified PR in one short loop-spec pass.
SkillAFreshness: AClaude Code +9 - 0.556score
status
aztechead
Shows where loop-spec runs stand in this repository: each run's phase, task graph, verify result, and PR.
SkillAFreshness: AClaude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get revise running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
revise skill. Agent Mart. https://agentmart.dev/skills/aztechead-revise (last updated 2026-10-24)