Agent skill

Audit Repo Issues

by kdeldycke in kdeldycke/dotfiles

Analyze a GitHub repository's issues and PRs to find unaddressed feature requests, dismissed ideas, maintenance signals, and opportunities relevant to the current project.

BSD-2-ClauseAuto-check passed

Install Audit Repo Issues

skills CLI
$ npx skills add kdeldycke/dotfiles --skill audit-repo-issues -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install kdeldycke/dotfiles audit-repo-issues --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/kdeldycke/dotfiles.git skills-src && mkdir -p .claude/skills && cp -r skills-src/dotfiles/.agents/skills/audit-repo-issues .claude/skills/audit-repo-issues && rm -rf skills-src

Use ~/.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/

Facts

Skill name
audit-repo-issues
GitHub stars
173
Token cost
~2.5k tokens
SKILL.md length
966 words
Files
1
Skills in repo
25
Repo updated
First seen
Licence
BSD-2-Clause

At a glance

Analyze a GitHub repository's issues and PRs to find unaddressed feature requests, dismissed ideas, maintenance signals, and opportunities relevant to the current project.

  • Works in 4 steps: Understand the current project → Gather data from the target repo → Triage and deep-dive → …
  • You want to scout a related
  • SKILL.md covers Goal, Workflow and Important rules
  • Calls gh

What it does

Audit Repo Issues is an agent skill from kdeldycke/dotfiles. Analyze a GitHub repository's issues and PRs to find unaddressed feature requests, dismissed ideas, maintenance signals, and opportunities relevant to the current project. Use when you want to scout a related or competing repo for gaps your project could fill.

Its SKILL.md is about 2.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts. Compatibility notes: Designed for Claude Code. Recommended model: Opus.

It works with GitHub. The repository describes itself as: 🍎 macOS dotfiles for Python developers. The licence is BSD-2-Clause.

When your agent uses it

  • You want to scout a related
  • Competing repo for gaps your project could fill

Example prompts

  • “/audit-repo-issues”

Requirements

  • Compatibility (from SKILL.md): Designed for Claude Code. Recommended model: Opus.

Workflow steps

4 steps, taken from the step headings in SKILL.md.

  1. Understand the current project
  2. Gather data from the target repo
  3. Triage and deep-dive
  4. Produce the report

What it can do on your machine

Read from SKILL.md and the folder at commit 37173b9. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • gh

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use gh, 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.

  • Compatibility

    Designed for Claude Code. Recommended model: Opus.

    From compatibility in the SKILL.md frontmatter.

Context cost

Audit Repo Issues loads about 2.5k tokens when it runs. Until then it costs about 70 tokens; SKILL.md has 966 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~70
When it runs · the whole SKILL.md, loaded when a task matches
~2.5k

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 passed

The automated check found no risky patterns in SKILL.md.

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 kdeldycke/dotfiles at commit 37173b9, republished under its BSD-2-Clause licence (© kdeldycke). 966 words, ~2,495 tokens.

Download SKILL.mdSave it as .claude/skills/audit-repo-issues/SKILL.md (or your agent's skills folder).
name
audit-repo-issues
description
Analyze a GitHub repository's issues and PRs to find unaddressed feature requests, dismissed ideas, maintenance signals, and opportunities relevant to the current project. Use when you want to scout a related or competing repo for gaps your project could fill.
compatibility
Designed for Claude Code. Recommended model: Opus.
argument-hint
{owner/repo}

Audit repository issues and PRs

Analyze a GitHub repository's open and closed issues and PRs to identify opportunities for the current project (the one in the working directory). The target repo is provided as $ARGUMENTS (e.g., python-distro/distro).

Goal

Produce a structured report covering:

  1. Popular unaddressed feature requests — open issues with high engagement (reactions, comments) that have stalled or been explicitly deferred.
  2. Dismissed feature requests — closed issues where maintainers rejected a popular idea, especially if it aligns with the current project's scope.
  3. Abandoned or rejected PRs — unmerged PRs that proposed valuable features, scope expansions, or new platform/detection support.
  4. Merged PRs worth noting — features that were added and could inform what the current project should also support.
  5. Maintenance and trust signals — evidence of maintenance gaps (stale PRs, slow releases, unanswered issues) that position the current project as a healthier alternative.
  6. Detection techniques or data sources — novel approaches proposed in issues/PRs that the current project could adopt.
  7. Commercial posture — whether the target is fully open-source, open-core-light, open-core-heavy, or fully proprietary, and which essential features (if any) live behind a paid tier.
  8. Retirement and acquisition signals — explicit notices that the project has been formally retired, superseded, or acquired with the roadmap shifted to a successor commercial product.

Workflow

Phase 1: Understand the current project
  1. Read the current project's CLAUDE.md, readme.md, or pyproject.toml to understand its scope, architecture, and what it already supports.
  2. This context determines what counts as "relevant" when scanning the target repo.
Phase 2: Gather data from the target repo

Use gh CLI exclusively. Run these searches in parallel where possible:

bash
# Open issues sorted by reactions (most popular first).
gh issue list -R $ARGUMENTS --state open --limit 100 --json number,title,labels,reactionGroups,comments,createdAt

# Closed issues (look for rejected feature requests).
gh issue list -R $ARGUMENTS --state closed --limit 200 --json number,title,labels,reactionGroups,comments,createdAt,closedAt

# Open PRs (potentially stalled).
gh pr list -R $ARGUMENTS --state open --limit 50 --json number,title,createdAt,comments

# Closed PRs (look for unmerged/rejected).
gh pr list -R $ARGUMENTS --state closed --limit 100 --json number,title,mergedAt,closedAt,comments,createdAt
Phase 3: Triage and deep-dive
  1. Rank issues by engagement: sort by total reactions + comment count.
  2. Identify feature requests: filter out pure bug reports — focus on enhancement requests, scope expansions, and architectural proposals.
  3. Deep-dive into top candidates: for the ~20 most promising issues/PRs, fetch full details:
    bash
    gh issue view -R $ARGUMENTS {number} --json title,body,comments,reactionGroups,labels,state,closedAt
    gh pr view -R $ARGUMENTS {number} --json title,body,comments,state,mergedAt,closedAt
  4. Check for current-project mentions: search for the current project's name in the target repo's issues to see if users have already referenced it as an alternative.
Phase 3b: Commercial posture and retirement check

For repos that ship a product (tools, datasets, projects — not articles or curation lists), evaluate the commercial posture and retirement signals. These rarely surface in issues/PRs, so check the repo metadata, README, and external pages directly.

bash
# Repo metadata: license, archive flag, latest push, latest release, homepage URL.
gh repo view $ARGUMENTS --json name,description,homepageUrl,licenseInfo,isArchived,pushedAt,latestRelease

# README contents (look for "premium features", "Enterprise", "Cloud", retirement notices).
gh api repos/$ARGUMENTS/readme --jq '.content' | base64 -d

# Top-level directory listing (look for ee/, enterprise/, pro/ folders that may carry a non-OSS license).
gh api repos/$ARGUMENTS/contents

Then assess each axis below. The first three define the commercial posture; the last two cover retirement.

AxisSignals to look forVerdict
License envelopelicenseInfo is permissive (MIT, Apache-2.0, BSD); no ee//enterprise//pro/ folder under a different licenseOSS-only
Feature gatingREADME mentions "Enterprise tier", "Cloud only", "premium features", "protective barrier"; pricing page lists SSO/SAML/OIDC, SCIM, audit log retention, multi-tenancy, fine-grained permissions, admin UI as paidOpen-core (light or heavy depending on which features are gated)
Vendor extractionHomepage URL is a vendor domain selling a hosted/Cloud/Enterprise version; pricing page exists; per-MAU or per-seat pricing on what looks like core featuresCommercial-backed
Formal retirementREADME banner pointing to a successor project; statement that "new projects should no longer rely on this"; archive flag set on the repoRetired
Acquisition driftRecent commits are Dependabot/copyright-only; no feature commits in 12+ months; pushedAt recent but latestRelease stale; vendor's roadmap mentions a successor commercial productMaintained-but-not-developed

Classify the project as one of: fully OSS, open-core-light (some advanced compliance/integrations gated, core works in OSS), open-core-heavy (essential features gated), fully proprietary (no usable OSS), retired, or acquisition-drifted. Spell out which essential features (per the current project's domain) are gated, if any.

Show full SKILL.md (383 more words)Show less
Phase 4: Produce the report

Structure the output as follows:

High-value opportunities

For each opportunity (sorted by relevance to the current project):

  • Issue/PR reference: number, title, link
  • Engagement: reaction count, comment count, age
  • Status: open/closed/rejected, and why
  • Relevance: how it maps to the current project's scope
  • Action: what the current project could do (already supports it, should add it, worth considering)
Platforms / features added to the target repo

List features that were merged into the target repo and that the current project might want to support too.

Detection techniques worth borrowing

Novel approaches or data sources proposed in issues/PRs.

Maintenance signals

Evidence table of maintenance health (stale PRs, release cadence, unanswered issues).

Commercial posture

State the verdict (fully OSS / open-core-light / open-core-heavy / fully proprietary / retired / acquisition-drifted). For open-core variants, list which essential features are gated and where (Enterprise tier, Cloud add-on, separate ee/ folder, per-MAU pricing). Include the vendor's pricing-page URL when relevant.

For curation tasks (e.g., feeding an awesome-list selection), use this verdict to decide:

  • Fully OSS → eligible, mark with the 🆓 marker if the awesome-list uses such markers.
  • Open-core-light → eligible when covering a distinct niche; mark with the 💸 marker.
  • Open-core-heavy → reject in overcrowded sections; the OSS shell is not genuinely usable in production.
  • Fully proprietary → reject when an OSS alternative exists; otherwise borderline.
  • Retired or acquisition-drifted → flag for removal even when the repo is not formally archived.
Retirement and acquisition signals

Quote any explicit retirement notice from the README, link the successor project if named, and call out acquisition-drift symptoms (Dependabot-only commits, stale latestRelease despite recent pushedAt, vendor roadmap shifted to a successor commercial product).

Bottom line

A concise summary of the biggest wins and positioning advantages.

Important rules

  • Use gh CLI for all GitHub API interactions — never scrape HTML.
  • Use the Agent tool to parallelize research across open issues, closed issues, and PRs.
  • When fetching issue/PR details, batch requests to avoid rate limiting.
  • Focus on relevance to the current project — skip issues about internal bugs, CI config, or typo fixes.
  • Include direct links to issues/PRs so the user can follow up.
  • If the target repo has thousands of issues, focus on the top 100 by engagement rather than trying to read everything.
  • Present findings with clear, scannable formatting (tables, headers, bullet points).
  • Do not editorialize beyond factual observations — let the data speak.

© kdeldycke, BSD-2-Clause. 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 dotfiles/.agents/skills/audit-repo-issues of kdeldycke/dotfiles.

Open the folder on GitHubat commit 37173b9

Compare with similar skills

Audit Repo Issues 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.

Audit Repo Issues compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Audit Repo Issues this skillkdeldycke/dotfiles173—~2.5kAutomated safety check: PassBSD-2-Clause
PR Babysitteropeninterpreter/openinterpreter69k3 repos~4.2kAutomated safety check: PassApache-2.0
Greplooponyx-dot-app/onyx32k4 repos~3.3kAutomated safety check: PassMIT
GitHub Deep Researchbytedance/deer-flow84k4 repos~1.3kAutomated safety check: PassMIT
Diagnosing Superpowers Sessionsobra/superpowers297k3 repos~1.7kAutomated safety check: PassMIT
Update V8 Versionopeninterpreter/openinterpreter69k2 repos~845Automated safety check: PassApache-2.0

Similar skills

  • PR Babysitter

    openinterpreter/openinterpreter

    Watches an open GitHub pull request until it merges, handling review comments, diagnosing CI failures and retrying flaky checks along the way.

    69k GitHub starsUsed in 3 repos~4.2k tokens
    DevelopmentAuto-check passed
  • Greploop

    onyx-dot-app/onyx

    Iteratively improves a PR (GitHub), MR (GitLab), or shelved changelist (Perforce) until Greptile gives it a 5/5 confidence score with zero unresolved comments.

    32k GitHub starsUsed in 4 repos~3.3k tokens
    DevelopmentAuto-check passed
  • GitHub Deep Research

    bytedance/deer-flow

    Researches a GitHub repository over four rounds using the GitHub API and web search, then writes a structured markdown report with timeline, metrics and Mermaid diagrams.

    84k GitHub starsUsed in 4 repos~1.3k tokens
    Research & ScienceAuto-check passed
  • Investigates a session where Superpowers went wrong, reads the transcripts on disk and produces an evidence-cited report, optionally prepared as a bug report for the maintainers.

    297k GitHub starsUsed in 3 repos~1.7k tokens
    Agent WorkflowsAuto-check passed
  • Update V8 Version

    openinterpreter/openinterpreter

    Bumps the pinned v8 and rusty_v8 versions in Codex, validates the release-candidate path with the v8-canary check, and traces failures to upstream build changes.

    69k GitHub starsUsed in 2 repos~845 tokens
    DevOps & CloudAuto-check passed
  • Last30days

    mvanhorn/last30days-skill

    Research what people actually say about any topic in the last 30 days.

    64k GitHub stars~7.9k tokensUpdated yesterday
    Research & ScienceAuto-check: notes

More from kdeldycke/dotfiles

All 25 skills in this repo
  • Agent Config Self Tune

    kdeldycke/dotfiles

    Audit and tune the configuration of coding agents across Claude Code and pi - settings files (settings.json, settings.local.json), permission rules, instruction files (CLAUDE.md, AGENTS.md), skill…

    173 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check: notes
  • Brand Assets

    kdeldycke/dotfiles

    Create project logo and banner SVGs, then export them to light and dark PNG variants.

    173 GitHub stars~4.7k tokensUpdated yesterday
    Auto-check passed
  • Fill Web Form

    kdeldycke/dotfiles

    Fill a web form using data extracted from local documents (PDFs, images, spreadsheets).

    173 GitHub stars~2.3k tokensUpdated yesterday
    Auto-check passed
  • Rename With Dates

    kdeldycke/dotfiles

    Rename documents and files (PDFs, images, screenshots, etc.) by reading their content to extract the effective/publication date, then renaming them with a "YYYY-MM-DD - Clear descriptive title.ext"…

    173 GitHub stars~3.5k tokensUpdated yesterday
    Auto-check passed
  • Repomatic Test Matrix

    kdeldycke/dotfiles

    Choose what a repository's CI test matrix covers. An agent skill from kdeldycke/dotfiles.

    173 GitHub stars~2.2k tokensUpdated yesterday
    Auto-check: notes
  • Sphinx Docs Sync

    kdeldycke/dotfiles

    Compare and synchronize Sphinx documentation against the upstream kdeldycke/repomatic reference, or across sibling projects.

    173 GitHub stars~3.2k tokensUpdated yesterday
    Auto-check: notes

Works with

Questions about Audit Repo Issues

What does Audit Repo Issues do?

Analyze a GitHub repository's issues and PRs to find unaddressed feature requests, dismissed ideas, maintenance signals, and opportunities relevant to the current project. Audit Repo Issues is an agent skill from kdeldycke/dotfiles. Analyze a GitHub repository's issues and PRs to find unaddressed feature requests, dismissed ideas, maintenance signals, and opportunities relevant to the current project.

When should I use Audit Repo Issues?

Audit Repo Issues fits situations like: you want to scout a related; competing repo for gaps your project could fill.

How do I install Audit Repo Issues in Claude Code?

Run `npx skills add kdeldycke/dotfiles --skill audit-repo-issues -a claude-code`. Or copy the skill folder (dotfiles/.agents/skills/audit-repo-issues in kdeldycke/dotfiles) into .claude/skills/audit-repo-issues in your project. Claude Code loads it when a task matches its description.

How do I install Audit Repo Issues in Codex?

Run `npx skills add kdeldycke/dotfiles --skill audit-repo-issues -a codex`. Or copy the skill folder (dotfiles/.agents/skills/audit-repo-issues in kdeldycke/dotfiles) into .agents/skills/audit-repo-issues in your project. Codex loads it when a task matches its description.

Can I use Audit Repo Issues 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 kdeldycke/dotfiles --skill audit-repo-issues -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-repo-issues, .gemini/skills/audit-repo-issues, .github/skills/audit-repo-issues and .opencode/skills/audit-repo-issues in your project.

What does Audit Repo Issues need to run?

Going by SKILL.md and its folder, Audit Repo Issues needs the command-line tools its instructions call (gh). Compatibility (from SKILL.md): Designed for Claude Code. Recommended model: Opus..

Does Audit Repo Issues access the network?

SKILL.md contains no URLs. Its commands use gh, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Audit Repo Issues safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Audit Repo Issues use?

Audit Repo Issues is published under the BSD-2-Clause licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Audit Repo Issues use?

About 2.5k tokens (SKILL.md is roughly 10k 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 Repo Issues?

Skills that share tags, products or a category with Audit Repo Issues: PR Babysitter (openinterpreter/openinterpreter, 69k stars), Greploop (onyx-dot-app/onyx, 32k stars), GitHub Deep Research (bytedance/deer-flow, 84k stars) and Diagnosing Superpowers Sessions (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Audit Repo Issues?

kdeldycke (a GitHub user) maintains it in kdeldycke/dotfiles, which has 173 GitHub stars. The repository holds 25 skills in this directory. The repository was last updated on October 9, 2026.

Source: kdeldycke/dotfiles on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.