Cursor Composer Task Delegate
Chachamaru127/claude-code-harness
Hands one implementation task to Cursor Composer in an isolated git worktree, then reviews its diff and cherry-picks the result into the main branch.
Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects.
Install Audit Analysis
$ npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install claesbackman/AI-research-feedback audit-analysis --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/claesbackman/AI-research-feedback.git skills-src && mkdir -p .claude/skills && cp -r skills-src/Skills/audit-analysis .claude/skills/audit-analysis && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "audit-analysis" agent skill from https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysis into .claude/skills/audit-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-analysis", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysisType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install claesbackman/AI-research-feedback audit-analysis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/claesbackman/AI-research-feedback.git skills-src && mkdir -p .agents/skills && cp -r skills-src/Skills/audit-analysis .agents/skills/audit-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "audit-analysis" agent skill from https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysis into .agents/skills/audit-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-analysis", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install claesbackman/AI-research-feedback audit-analysis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/claesbackman/AI-research-feedback.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/Skills/audit-analysis .cursor/skills/audit-analysis && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "audit-analysis" agent skill from https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysis into .cursor/skills/audit-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-analysis", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/claesbackman/AI-research-feedback.git --path Skills/audit-analysis--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install claesbackman/AI-research-feedback audit-analysis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/claesbackman/AI-research-feedback.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/Skills/audit-analysis .gemini/skills/audit-analysis && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "audit-analysis" agent skill from https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysis into .gemini/skills/audit-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-analysis", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install claesbackman/AI-research-feedback audit-analysisInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/claesbackman/AI-research-feedback.git skills-src && mkdir -p .github/skills && cp -r skills-src/Skills/audit-analysis .github/skills/audit-analysis && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "audit-analysis" agent skill from https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysis into .github/skills/audit-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-analysis", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install claesbackman/AI-research-feedback audit-analysis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/claesbackman/AI-research-feedback.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/Skills/audit-analysis .opencode/skills/audit-analysis && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "audit-analysis" agent skill from https://github.com/claesbackman/AI-research-feedback/tree/main/Skills/audit-analysis into .opencode/skills/audit-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "audit-analysis", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
audit-analysis- GitHub stars
- 491
- Token cost
- ~1.1k tokens
- SKILL.md length
- 621 words
- Files
- 1
- Skills in repo
- 10
- Repo updated
- First seen
- Licence
- MIT
At a glance
Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects.
- Works in 3 steps: Establish scope → Launch the auditor → Relay without softening
- Tasks that involve Reproducible research
- SKILL.md covers Phase 1: Establish scope, Phase 2: Launch the auditor and Phase 3: Relay without softening
- Calls git
What it does
Audit Analysis is an agent skill from claesbackman/AI-research-feedback. Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects. Runs in an isolated subagent. Use before circulating results or submitting. This is not a reproducibility or paper-to-code review — use review-paper-code for that.
Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Development, covering Reproducible research and Subagents. It works with Git. The repository describes itself as: A collection of Claude Code skills for academic research review. These tools were developed by Claes Bäckman. The licence is MIT.
When your agent uses it
- Tasks that involve Reproducible research
- Tasks that involve Subagents
Example prompts
- “/audit-analysis”
Requirements
- Pre-approved tools (allowed-tools): Bash, Read, Grep, Glob, Agent
Workflow steps
3 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit d129756. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves these tools, so the agent can use them without asking each time:
BashReadGrepGlobAgent
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
git
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Audit Analysis loads about 1.1k tokens when it runs. Until then it costs about 94 tokens; SKILL.md has 621 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check: notes
The automated check noted patterns worth knowing about, such as sudo or a known installer.
- NotePre-approves every shell command (allowed-tools: Bash)SKILL.md
allowed-tools: Bash, Read, Grep, Glob, Agent
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from claesbackman/AI-research-feedback at commit d129756, republished under its MIT licence (© claesbackman). 621 words, ~1,116 tokens.
Download SKILL.mdSave it as
.claude/skills/audit-analysis/SKILL.md (or your agent's skills folder).- name
- audit-analysis
- description
- Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects. Runs in an isolated subagent. Use before circulating results or submitting. This is not a reproducibility or paper-to-code review — use review-paper-code for that.
- allowed-tools
- Bash, Read, Grep, Glob, Agent
- argument-hint
- [optional: base ref, default main]
- disable-model-invocation
- true
Audit Analysis Code
Find errors in changed empirical code before a referee does.
The audit runs in a subagent with a clean context. That isolation is the point: whoever wrote the code — including this session, if it helped — must not be able to steer the findings. Do not read the changed files yourself before launching, do not form a view, and do not answer the auditor's questions mid-run.
Phase 1: Establish scope
Set BASE from $ARGUMENTS if given, otherwise main.
Run, and stop with a short explanation if any of the first three fail:
git rev-parse --git-dir— must be a repositorygit rev-parse --verify BASE— the base ref must existgit diff --stat BASE— if empty, there is nothing to auditgit log BASE..HEAD --oneline— may legitimately be empty when the work is uncommitted, or when HEAD is BASE and only the working tree has changed. Note it and drop the commit-message check from the audit.
Report to the user in two or three lines: base ref, number of changed files, number of changed lines, and whether commit messages are available. Then launch immediately.
Phase 2: Launch the auditor
One Agent call, subagent_type: "general-purpose". Substitute BASE and pass this verbatim:
Review empirical research code adversarially. The author wants it broken now rather than by a referee. Read
git log BASE..HEADandgit diff BASE, then the changed files in full. Follow variables built outside the diff.Check, and report on each of:
- Claims vs. code: do comments and commit messages match what runs? Quote both sides of any disagreement.
- Sample: N before and after every filter, merge, and collapse. Take N from logs; write "N unverified" where there is no log. Flag undocumented drops.
- Merges: key, uniqueness on the side that needs it, fate of unmatched observations, whether
_mergeis inspected, duplicate id-period pairs after.- Variables: trace every regressor and outcome. Units, logs vs. levels, deflation, lag alignment. Does construction match the name?
- Silent failures: missings coerced to zero,
if x > 0true on missing,destring ... force,replacethat changes nothing, loops that skip. In Python,fillna(0), silent dtype coercion, chained assignment.- Estimation: clustering level and cluster count, what the fixed effects absorb, weights, whether estimation N matches the sample traced above.
Each finding: file, line, quoted excerpt, what is wrong, consequence for the results. Tag CONFIRMED (visible in the code) or SUSPECTED (needs the data). Style and naming are not findings. Order by consequence, worst first, ten max. Then one line per category: what you found, or that you found nothing. Close with the one thing you could not check without the data. Change nothing.
Show full SKILL.md (185 more words)Show less
If the diff exceeds roughly 1,500 changed lines, run two auditors in parallel instead — one taking claims, sample, and merges, the other taking variables, silent failures, and estimation — and concatenate their findings. Do not split a smaller diff; the categories inform each other.
Phase 3: Relay without softening
Pass the findings through in the order returned, worst first. Do not reclassify a SUSPECTED finding as fine, do not add reassurance, and do not open with what the code gets right. The user asked for errors.
Drop any finding that lacks a file, a line, and a quoted excerpt, and tell the user how many you dropped. Unanchored findings are the failure mode this design exists to catch — an auditor told to find errors will manufacture them if nothing forces it to point at code.
Reproduce the per-category coverage lines verbatim, including the categories that came back clean, and the closing line about what could not be checked without the data. A clean category is a claim the auditor is on the record for.
Fix nothing. If the user wants repairs, that is a separate request.
© claesbackman, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in Skills/audit-analysis of claesbackman/AI-research-feedback.
Open the folder on GitHubat commit d129756
Compare with similar skills
Audit Analysis next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Audit Analysis this skillclaesbackman/AI-research-feedback | 491 | — | ~1.1k | Automated safety check: Notes | MIT | |
| Cursor Composer Task DelegateChachamaru127/claude-code-harness | 3.2k | — | ~4.4k | Automated safety check: Notes | MIT | |
| Firewood Reviewava-labs/firewood | 153 | — | ~2.1k | Automated safety check: Notes | Custom licence | |
| Tutti Architecture Reviewtutti-os/tutti | 3.8k | — | ~2.3k | Automated safety check: Pass | Apache-2.0 | |
| PR Monitoring Loopelastic/terraform-provider-elasticstack | 210 | — | ~4.1k | Automated safety check: Pass | MIT | |
| Parallel Adversarial Change Reviewben-manes/caffeine | 18k | — | ~1.9k | Automated safety check: Notes | Apache-2.0 |
Similar skills
Firewood Review
ava-labs/firewood
A skill your agent uses when reviewing ava-labs/firewood code changes — pull request or local workspace.
Tutti Architecture Review
tutti-os/tutti
Review tutti git diffs for project structure, layering, module ownership, and duplicate event-center infrastructure by planning focused architecture review tasks, then having the main agent…
- Official
PR Monitoring Loop
elastic/terraform-provider-elasticstack
Monitor GitHub pull requests through a subagent-based loop that watches CI checks, review comments, PR comments, review state, merge conflicts, and branch freshness.
Parallel Adversarial Change Review
ben-manes/caffeine
Runs three parallel reviewers on a diff or branch, one blind, one design-aware and one matching past bug patterns, then triages their findings.
Veomni Review
ByteDance-Seed/VeOmni
Pre-PR code review gate. An agent skill from ByteDance-Seed/VeOmni.
More from claesbackman/AI-research-feedback
All 10 skills in this repoExplorable Deck
claesbackman/AI-research-feedback
Build a Quarto reveal.js slide deck in the explorable-explanation style (Nicky Case) — one idea per slide, assertion titles, a concrete running example, run-time SVG stages the presenter drives…
PDF To Markdown
claesbackman/AI-research-feedback
Split a PDF into chunks and convert it to readable markdown text.
Review Paper Light
claesbackman/AI-research-feedback
Run a fast 2-agent pre-submission check for an economics paper — focuses on contribution, identification, and causal overclaiming.
Paper Version
claesbackman/AI-research-feedback
Convert a LaTeX research paper into a policy brief, 1-page summary, or 5-page summary for a general audience, with factual review and a standalone HTML page for GitHub Pages.
Review Grant
claesbackman/AI-research-feedback
Run a 6-agent pre-submission panel review for a grant proposal targeting a specified funder or program
Review Paper Checks
claesbackman/AI-research-feedback
Run a fast 3-agent mechanical check of an economics paper — spelling and grammar, internal consistency and cross-references, and unsupported claims.
Related
Works with
Categories
Questions about Audit Analysis
What does Audit Analysis do?
Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects. Audit Analysis is an agent skill from claesbackman/AI-research-feedback. Adversarially audit changed analysis code against a base ref, hunting for correctness errors in sample construction, merges, variable construction, silent failures, and clustering or fixed effects.
When should I use Audit Analysis?
Audit Analysis fits situations like: tasks that involve Reproducible research; tasks that involve Subagents.
How do I install Audit Analysis in Claude Code?
Run `npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a claude-code`. Or copy the skill folder (Skills/audit-analysis in claesbackman/AI-research-feedback) into .claude/skills/audit-analysis in your project. Claude Code loads it when a task matches its description.
How do I install Audit Analysis in Codex?
Run `npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a codex`. Or copy the skill folder (Skills/audit-analysis in claesbackman/AI-research-feedback) into .agents/skills/audit-analysis in your project. Codex loads it when a task matches its description.
Can I use Audit Analysis in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add claesbackman/AI-research-feedback --skill audit-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/audit-analysis, .gemini/skills/audit-analysis, .github/skills/audit-analysis and .opencode/skills/audit-analysis in your project.
What does Audit Analysis need to run?
Going by SKILL.md and its folder, Audit Analysis needs the command-line tools its instructions call (git). Its frontmatter pre-approves these tools: Bash, Read, Grep, Glob, Agent.
Does Audit Analysis access the network?
SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.
Is Audit Analysis safe to install?
Our automated static check of SKILL.md found notes only (pre-approves every shell command (allowed-tools: bash)), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.
What licence does Audit Analysis use?
Audit Analysis is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Audit Analysis use?
About 1.1k tokens (SKILL.md is roughly 4.5k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Audit Analysis?
Skills that share tags, products or a category with Audit Analysis: Cursor Composer Task Delegate (Chachamaru127/claude-code-harness, 3.2k stars), Firewood Review (ava-labs/firewood, 153 stars), Tutti Architecture Review (tutti-os/tutti, 3.8k stars) and PR Monitoring Loop (elastic/terraform-provider-elasticstack, 210 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Audit Analysis?
claesbackman (a GitHub user) maintains it in claesbackman/AI-research-feedback, which has 491 GitHub stars. The repository holds 10 skills in this directory. The repository was last updated on September 25, 2026.
Source: claesbackman/AI-research-feedback on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.