Agent skill

Playbook CLI Audit

by PackmindHub in PackmindHub/packmind

Audit all packmind- skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally installed Packmind CLI.

Apache-2.0Auto-check passed

Install Playbook CLI Audit

skills CLI
$ npx skills add PackmindHub/packmind --skill playbook-cli-audit -a claude-code

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

GitHub CLI
$ gh skill install PackmindHub/packmind playbook-cli-audit --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/PackmindHub/packmind.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/playbook-cli-audit .claude/skills/playbook-cli-audit && 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
playbook-cli-audit
GitHub stars
317
Token cost
~2.2k tokens
SKILL.md length
907 words
Files
1
Skills in repo
35
Repo updated
First seen
Licence
Apache-2.0

At a glance

Audit all packmind- skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally installed Packmind CLI.

  • Works in 5 steps: Establish CLI Surface → Discover and Scan Skills → Cross-Reference and Detect Issues → …
  • You want to check that skills referencing packmind-cli are up to date
  • SKILL.md covers Phase 1: Establish CLI Surface, Phase 2: Discover and Scan…, Phase 3: Cross-Reference and… and Phase 4: Generate Report, plus 1 more section
  • Calls node

What it does

Playbook CLI Audit is an agent skill from PackmindHub/packmind. Audit all packmind- skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally installed Packmind CLI. Use when you want to check that skills referencing packmind-cli are up to date, after a CLI upgrade, before a release, or whenever you suspect skills may reference outdated CLI commands. Also triggers on phrases like "audit CLI usage", "check skills for CLI issues", "are my skills up to date with the CLI", or "CLI…

Its SKILL.md is about 2.2k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

The repository describes itself as: Packmind seamlessly captures your engineering playbook and turns it into AI context, guardrails, and governance. The licence is Apache-2.0.

When your agent uses it

  • You want to check that skills referencing packmind-cli are up to date
  • After a CLI upgrade
  • Before a release
  • Whenever you suspect skills may reference outdated CLI commands

Example prompts

  • “audit CLI usage”
  • “check skills for CLI issues”
  • “are my skills up to date with the CLI”
  • “/playbook-cli-audit”

Workflow steps

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

  1. Establish CLI Surface
  2. Discover and Scan Skills
  3. Cross-Reference and Detect Issues
  4. Generate Report
  5. Present to User

What it can do on your machine

Read from SKILL.md and the folder at commit 858ed50. 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:

    • node

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

  • Network

    No URLs in SKILL.md.

    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

Playbook CLI Audit loads about 2.2k tokens when it runs. Until then it costs about 139 tokens; SKILL.md has 907 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~139
When it runs · the whole SKILL.md, loaded when a task matches
~2.2k

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 PackmindHub/packmind at commit 858ed50, republished under its Apache-2.0 licence (© PackmindHub). 907 words, ~2,240 tokens.

Download SKILL.mdSave it as .claude/skills/playbook-cli-audit/SKILL.md (or your agent's skills folder).
name
playbook-cli-audit
description
Audit all packmind-* skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally installed Packmind CLI. Use when you want to check that skills referencing packmind-cli are up to date, after a CLI upgrade, before a release, or whenever you suspect skills may reference outdated CLI commands. Also triggers on phrases like "audit CLI usage", "check skills for CLI issues", "are my skills up to date with the CLI", or "CLI compatibility check".

Playbook CLI Audit

Detect incompatibilities between the packmind-* skills deployed in .claude/skills/ and the current Packmind CLI. Skills evolve independently from the CLI — when the CLI deprecates or removes commands, renames flags, or changes accepted file formats, skills can silently break. This audit catches those issues before users hit them at runtime.

This skill only detects issues — it does not fix them.

Phase 1: Establish CLI Surface

Build the authoritative map of what the CLI currently supports.

1.1 Get CLI version
bash
node ./dist/apps/cli/main.cjs --version

Remember this as $CLI_VERSION (e.g., 0.26.0). If the command fails, try packmind-cli --version as a fallback. If both fail, stop and tell the user the CLI is not available.

1.2 Build the command map from CLI source code

The CLI command definitions live in apps/cli/src/infra/commands/. Read the command registration files to build a complete map of:

  • Available top-level commands and their subcommands
  • Accepted options/flags for each command (names, types, whether required)
  • Accepted argument types (file paths, strings, etc.) and any format constraints
  • Deprecated commands — look for [Deprecated] in descriptions and has been removed in handler code
  • Migration paths — what the deprecated command's error message suggests instead

Structure this internally as a reference table. Here is the expected shape — adapt if the source reveals more or fewer commands:

CommandStatusAccepted InputsKey FlagsMigration
standards createREMOVEDJSON file/stdin--space, --from-skillplaybook add <path>
commands createREMOVEDJSON file/stdin--space, --from-skillplaybook add <path>
skills addREMOVEDdirectory path--space, --from-skillplaybook add <path>
install --listREMOVED——packages list
install --showREMOVED——packages show <slug>
diffDEPRECATED—--submit, -mplaybook diff, playbook submit
diff addDEPRECATEDfile path-mplaybook add
lint --diffDEPRECATED——--changed-files / --changed-lines
playbook addACTIVE.md, .mdc files--space—
playbook submitACTIVE—-m (needed in non-TTY)—
packages addACTIVE—--to, --standard/--command/--skill (one type per call)—
...............

Do not hardcode this table — read the actual source in apps/cli/src/infra/commands/ to build it. The table above is a starting point to orient your search, not the source of truth.

1.3 Print summary
CLI version: $CLI_VERSION
Commands mapped: N active, M deprecated/removed

Phase 2: Discover and Scan Skills

2.1 Find all packmind-* skills

Glob .claude/skills/packmind-*/ to find all skill directories. For each, collect:

  • SKILL.md (the main instruction file)
  • All files in subdirectories (references/, steps/, scripts/, packmind-versions/, etc.)
2.2 Handle version-specific subdirectories

Some skills contain packmind-versions/<semver>/ directories with version-specific instructions. The version resolution logic works like this:

  1. List all version directories (e.g., 0.21.0/, 0.23.0/)
  2. Compare each against $CLI_VERSION
  3. A version directory is in scope if it is the highest version that is <= $CLI_VERSION
  4. Version directories that are not in scope (lower versions superseded by a higher one that is still <= $CLI_VERSION) should be flagged as INFO-level findings ("version 0.21.0 is superseded by 0.23.0 for CLI $CLI_VERSION") but their CLI invocations still need to be checked — they may still be reachable by users with older CLI versions

Example: If $CLI_VERSION is 0.25.0 and the skill has 0.21.0/ and 0.23.0/:

  • 0.23.0/ is the active version (highest <= 0.25.0)
  • 0.21.0/ is superseded but still scanned
2.3 Extract CLI invocations

For every file in scope, extract all lines that invoke the CLI. Look for these patterns:

  • packmind-cli <anything> — the primary pattern
  • node ./dist/apps/cli/main.cjs <anything> — local dev invocation
  • Code blocks containing CLI commands (inside ``` fences)
  • Inline code references (inside ` backticks)
  • Plain-text references in prose (e.g., "Run packmind-cli standards create")

For each invocation, parse:

  • Command: the top-level command (e.g., standards)
  • Subcommand: if any (e.g., create)
  • Arguments: positional args (e.g., file paths)
  • Flags/options: named options (e.g., --space, -m)
  • Source location: file path and line number
Show full SKILL.md (326 more words)Show less

Phase 3: Cross-Reference and Detect Issues

For each extracted CLI invocation, check it against the command map from Phase 1. Detect these categories of issues:

CRITICAL — Will fail at runtime
CheckDescriptionExample
Removed commandInvocation uses a command the CLI has removedstandards create → removed, use playbook add
Non-existent commandCommand or subcommand does not exist in the CLIpackmind-cli list standards (correct: standards list)
Invalid file formatFile type passed to a command that doesn't accept it.json file to playbook add (accepts only .md/.mdc)
Mixed artifact typespackages add called with multiple artifact type flags--standard X --command Y in one call
WARNING — May fail or produce unexpected behavior
CheckDescriptionExample
Deprecated commandCommand works but shows deprecation warningdiff add → use playbook add
Missing required flag in agent contextCommand lacks a flag needed in non-interactive/CI contextsplaybook submit without -m opens an editor
Deprecated flagA specific flag is deprecatedlint --diff → use --changed-files
Incorrect install syntaxinstall --list or install --show used instead of packages list/packages showpackmind-cli install --list
INFO — Worth noting
CheckDescriptionExample
Superseded version directoryA version-specific directory is no longer the active one0.21.0/ when 0.23.0/ exists and CLI is >= 0.23.0
CLI version metadata mismatchSkill frontmatter declares packmind-cli-version that conflicts with installed versionpackmind-cli-version: "< 0.25.0" when CLI is 0.26.0
Undocumented flag usageA flag is used that doesn't appear in the command definitionMay indicate a removed or renamed flag

Phase 4: Generate Report

Write the report to playbook-cli-audit-report.md at the project root.

Report Structure
markdown
# Playbook CLI Audit Report

**Generated**: {date}
**CLI version**: {$CLI_VERSION}
**Skills scanned**: {count}
**Files analyzed**: {count}

## Summary

| Severity | Count |
|---|---|
| CRITICAL | {n} |
| WARNING | {n} |
| INFO | {n} |

## Findings

### CRITICAL

#### {n}. [{skill-name}] {short description}

- **File**: `{path}:{line}`
- **Invocation**: `{the CLI command as written in the skill}`
- **Issue**: {what's wrong}
- **Fix**: {what the command should be replaced with}

### WARNING

...same structure...

### INFO

...same structure...

## Skills Scanned

| Skill | Files | Invocations | Issues |
|---|---|---|---|
| packmind-onboard | 19 | 12 | 5 CRITICAL, 1 WARNING |
| packmind-update-playbook | 8 | 15 | 0 |
| ... | ... | ... | ... |

## CLI Command Surface Reference

List of all active commands with their accepted inputs, for quick cross-reference.
If no issues are found
markdown
# Playbook CLI Audit Report

**Generated**: {date}
**CLI version**: {$CLI_VERSION}
**Skills scanned**: {count}

All packmind-* skills are compatible with the installed CLI version. No issues found.

Phase 5: Present to User

After writing the report:

  1. Print a summary to the conversation:
    • Total CRITICAL / WARNING / INFO counts
    • Top 3 most affected skills
    • The report file path
  2. If there are CRITICAL findings, highlight them explicitly — these are commands that will fail when users invoke the skill

Do not suggest fixes automatically. The user decides how to address each finding.

© PackmindHub, Apache-2.0. 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 .agents/skills/playbook-cli-audit of PackmindHub/packmind.

Open the folder on GitHubat commit 858ed50

Compare with similar skills

Playbook CLI Audit 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.

Playbook CLI Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Playbook CLI Audit this skillPackmindHub/packmind317—~2.2kAutomated safety check: PassApache-2.0
Deprecate APIremotion-dev/remotion62k—~529Automated safety check: PassCustom licence
Manage Deprecationsquarkusio/quarkus16k—~2.8kAutomated safety check: PassApache-2.0
Flet Deprecationflet-dev/flet17k—~2.2kAutomated safety check: PassApache-2.0
Aria Deprecated Rolethedaviddias/Front-End-Checklist74k—~441Automated safety check: PassMIT
ML Adoption Playbookaffaan-m/ECC274k1 repos~975Automated safety check: PassMIT

Similar skills

  • Deprecate API

    remotion-dev/remotion

    Official

    Reference for how deprecation of public Remotion APIs is represented in TypeScript source and documentation.

    62k GitHub stars~529 tokensUpdated today
    Media & CreativeAuto-check passed
  • Manage Deprecations

    quarkusio/quarkus

    Maintain @Deprecated code in the Quarkus codebase: remove code that has been deprecated for more than 12 months, add the @Deprecated annotations that were missed when a related element was…

    16k GitHub stars~2.8k tokensUpdated yesterday
    Auto-check passed
  • Flet Deprecation

    flet-dev/flet

    A skill your agent uses when adding or changing deprecations for Python controls/APIs in sdk/python/packages/, including V.deprecated fields, deprecated decorators, version lifecycle, and docs…

    17k GitHub stars~2.2k tokensUpdated today
    Auto-check passed
  • Aria Deprecated Role

    thedaviddias/Front-End-Checklist

    A skill your agent uses when reviewing rendered HTML, interactive components, or design-system patterns related to Avoid using deprecated ARIA roles.

    74k GitHub stars~441 tokensUpdated yesterday
    Frontend & DesignAuto-check passed
  • End-to-end methodology for AI agents and software engineers to add machine learning algorithms to existing non-ML codebases.

    274k GitHub starsUsed in 1 repo~975 tokens
    Data & AnalyticsAuto-check passed
  • Onboarding Playbook

    sickn33/agentic-awesome-skills

    Onboarding checklist: step, phase and order, department, owner, linked SOP and required flag.

    47k GitHub starsUsed in 1 repo~3.1k tokens
    Business, Finance & HRAuto-check passed

More from PackmindHub/packmind

All 35 skills in this repo
  • Michel CLI Demo Recorder

    PackmindHub/packmind

    Produce proof-of-execution demos of the Packmind CLI (packmind-cli) as terminal-styled images (colors and formatting preserved exactly), for embedding in a GitHub PR.

    317 GitHub stars~3.4k tokensUpdated yesterday
    Auto-check passed
  • Michel UI Demo Recorder

    PackmindHub/packmind

    Record polished UI demo videos and screenshots of a running web app using Playwright MCP — for client deliverables, release notes, feature walkthroughs, or bug repros.

    317 GitHub stars~6.4k tokensUpdated yesterday
    Auto-check passed
  • Packmind Create Skill

    PackmindHub/packmind

    Guide for creating effective skills. An agent skill from PackmindHub/packmind.

    317 GitHub stars~3.5k tokensUpdated yesterday
    Auto-check: notes
  • Doc Audit

    PackmindHub/packmind

    Audit Packmind end-user documentation (apps/doc/) for broken links, outdated CLI references, non-existent concepts, misleading information, and missing coverage.

    317 GitHub stars~2.4k tokensUpdated yesterday
    Auto-check passed
  • Feature Sprint

    PackmindHub/packmind

    Execute the implementation plan produced by /feature-spec. An agent skill from PackmindHub/packmind.

    317 GitHub stars~1.9k tokensUpdated yesterday
    Auto-check passed
  • Review an implemented GitHub issue the way a senior Packmind engineer would — the human-judgment checks that ESLint, the TypeScript compiler, and e2e tests cannot catch (authorization scoping…

    317 GitHub stars~2.7k tokensUpdated yesterday
    Auto-check passed

Questions about Playbook CLI Audit

What does Playbook CLI Audit do?

Audit all packmind- skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally installed Packmind CLI. Playbook CLI Audit is an agent skill from PackmindHub/packmind. Audit all packmind- skills for CLI compatibility issues: deprecated commands, invalid options, wrong file formats, missing flags, and version mismatches against the locally installed Packmind CLI.

When should I use Playbook CLI Audit?

Playbook CLI Audit fits situations like: you want to check that skills referencing packmind-cli are up to date; after a CLI upgrade; before a release; whenever you suspect skills may reference outdated CLI commands.

How do I install Playbook CLI Audit in Claude Code?

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

How do I install Playbook CLI Audit in Codex?

Run `npx skills add PackmindHub/packmind --skill playbook-cli-audit -a codex`. Or copy the skill folder (.agents/skills/playbook-cli-audit in PackmindHub/packmind) into .agents/skills/playbook-cli-audit in your project. Codex loads it when a task matches its description.

Can I use Playbook CLI Audit 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 PackmindHub/packmind --skill playbook-cli-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/playbook-cli-audit, .gemini/skills/playbook-cli-audit, .github/skills/playbook-cli-audit and .opencode/skills/playbook-cli-audit in your project.

What does Playbook CLI Audit need to run?

Going by SKILL.md and its folder, Playbook CLI Audit needs the command-line tools its instructions call (node).

Does Playbook CLI Audit access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is Playbook CLI Audit 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 Playbook CLI Audit use?

Playbook CLI Audit is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Playbook CLI Audit use?

About 2.2k tokens (SKILL.md is roughly 9k 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 Playbook CLI Audit?

Skills that share tags, products or a category with Playbook CLI Audit: Deprecate API (remotion-dev/remotion, 62k stars), Manage Deprecations (quarkusio/quarkus, 16k stars), Flet Deprecation (flet-dev/flet, 17k stars) and Aria Deprecated Role (thedaviddias/Front-End-Checklist, 74k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Playbook CLI Audit?

PackmindHub (a GitHub organization) maintains it in PackmindHub/packmind, which has 317 GitHub stars. The repository holds 35 skills in this directory. The repository was last updated on October 6, 2026.

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