Agent skill

Decision Audit

by gnurio in gnurio/nurijanian-skills

PM decision quality auditor. An agent skill from gnurio/nurijanian-skills.

MITAuto-check passed

Install Decision Audit

skills CLI
$ npx skills add gnurio/nurijanian-skills --skill decision-audit -a claude-code

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

GitHub CLI
$ gh skill install gnurio/nurijanian-skills decision-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/gnurio/nurijanian-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/decision-audit .claude/skills/decision-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
decision-audit
GitHub stars
124
Token cost
~1.7k tokens
SKILL.md length
927 words
Files
2 (incl. references)
Skills in repo
15
Repo updated
First seen
Licence
MIT

At a glance

PM decision quality auditor. An agent skill from gnurio/nurijanian-skills.

  • Works in 4 steps: Get the Decision → The Audit Interview → Score the Decision → …
  • A PM wants to audit a specific decision they made — not just whether it worked out
  • SKILL.md covers What This Mode Does, Process, The Core Principle to Enforce and Calibration Notes, plus 1 more section
  • Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md

What it does

Decision Audit is an agent skill from gnurio/nurijanian-skills. PM decision quality auditor. Use this skill whenever a PM wants to audit a specific decision they made — not just whether it worked out, but whether it was a good decision by the criteria that define PM excellence. Trigger on: "was this the right call?", "I want to audit this decision", "I'm not sure I made this well", "help me think through whether this was a good PM decision", "I made a call about X and I want to pressure-test it", "I cut this feature / changed this priority / chose this direction — was that…

Its SKILL.md is about 1.7k tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files, including reference files (for example `references/pm-excellence-behaviors.md`).

The repository describes itself as: Claude Code and Cursor skills for product managers — PM coaching, verbalized sampling, tech sensemaking, and more. The licence is MIT.

When your agent uses it

  • A PM wants to audit a specific decision they made — not just whether it worked out
  • But whether it was a good decision by the criteria that define PM excellence
  • : was this the right call?
  • I want to audit this decision

Example prompts

  • “was this the right call?”
  • “I want to audit this decision”
  • “m not sure I made this well”
  • “/decision-audit”

Workflow steps

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

  1. Get the Decision
  2. The Audit Interview
  3. Score the Decision
  4. Deliver the Audit

What it can do on your machine

Read from SKILL.md and the folder at commit 43a0566. 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

    No scripts in the folder and no shell commands in SKILL.md.

    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

Decision Audit loads about 1.7k tokens when it runs, and up to ~4k if it reads all its reference files. Until then it costs about 204 tokens; SKILL.md has 927 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~204
When it runs · the whole SKILL.md, loaded when a task matches
~1.7k
With references · SKILL.md plus every file in references/, read only if the agent opens them
~4k

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 gnurio/nurijanian-skills at commit 43a0566, republished under its MIT licence (© gnurio). 927 words, ~1,742 tokens.

Download SKILL.mdSave it as .claude/skills/decision-audit/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.
name
decision-audit
description
PM decision quality auditor. Use this skill whenever a PM wants to audit a specific decision they made — not just whether it worked out, but whether it was a *good decision* by the criteria that define PM excellence. Trigger on: "was this the right call?", "I want to audit this decision", "I'm not sure I made this well", "help me think through whether this was a good PM decision", "I made a call about X and I want to pressure-test it", "I cut this feature / changed this priority / chose this direction — was that right?", or any time a PM wants structured feedback on the quality of a specific decision they made, regardless of whether it turned out well. Important: good outcomes don't make good decisions; bad outcomes don't make bad decisions. This skill audits the *process*, not the result.

Decision Audit

Read references/pm-excellence-behaviors.md before beginning. Focus on Cluster 2 (Decision Quality) as the primary lens, with Clusters 1, 3, and 6 as secondary lenses for how the decision was made and communicated.

What This Mode Does

The PM describes a decision they made. You walk them through a structured audit of the decision process — not whether it worked out, but whether it was made with the rigor, transparency, and customer-centricity that defines excellent PM decision-making.

The output is a decision quality scorecard and a clear statement of where the process fell short.


Process

Step 1: Get the Decision

Ask the PM to describe the decision. You need:

  • What was decided? (feature cut, priority change, direction call, scope trade-off, etc.)
  • When? (recent enough that details are fresh)
  • What was the alternative? (every decision has a road not taken — what was it?)
  • What happened? (outcome so far, if any)

If they've already described it, work with what you have.

Step 2: The Audit Interview

Ask these questions one at a time. Don't ask all of them at once — listen and adjust based on what they say:

On data and grounding: "What data or research informed this decision? Walk me through what you looked at."

On the customer: "Where does the customer appear in the reasoning? How did user impact factor into the call?"

On alternatives: "What was the strongest argument for the alternative you didn't choose? Did you seriously consider it?"

On transparency: "How did you communicate the decision to the team? Did you share the 'why' or just the 'what'?"

On reversibility: "Was this a reversible or irreversible decision? Did you treat it accordingly — i.e., move fast on reversible, slow down on irreversible?"

On pressure: "Was there any external pressure (leadership, timeline, politics) that shaped this decision? If so, how did you account for it?"

On dissent: "Did anyone push back? If so, what happened to that pushback?"

You won't always need all six questions. If the PM has already addressed something, move on.

Step 3: Score the Decision

Silently assess the decision against five dimensions (don't show the scores — use them to structure your output):

DimensionWhat "Good" Looks LikeWhat "Weak" Looks Like
Customer-centricityUser impact explicitly weighed; customer used as north starDecision driven by business pressure, personal preference, or technical convenience
Data qualityRelevant data identified and used correctly; gaps acknowledgedNo data, bad data, or data cherry-picked to support a pre-made call
Transparency"Why" shared proactively; team could reconstruct the reasoning"What" communicated, "why" assumed or withheld
Alternative considerationStrongest counter-argument taken seriously and addressedOnly one option considered; alternative dismissed superficially
Appropriate speedReversible decisions made fast; irreversible ones slowed down for inputAll decisions treated the same, regardless of reversibility
Step 4: Deliver the Audit

Structure your output as:

The quality of this decision: Open with a direct, one-sentence read: "This was a solid decision made from a weak data position" or "This was the right call, but it was made in a way that probably eroded team trust" or "This decision had good intent but was process-poor."

What you got right: Name 1-2 genuine strengths in how the decision was made. Be specific.

Where the process broke down: Name the 1-3 most significant process failures. For each:

  • What the failure was (specifically)
  • Why it matters — what does it cost the team or the product in the long run?
  • What doing it differently would look like

The distinction that matters most: End with the one insight that cuts to the heart of the decision. This might be about process ("you outsourced the 'why' to leadership, which means your team can't evaluate the decision themselves"), about timing ("this needed to be a slow decision — reversible decisions can move fast, this one couldn't"), or about the customer ("the user never appeared in your reasoning — that's the tell").


Show full SKILL.md (285 more words)Show less

The Core Principle to Enforce

The best PMs in the source material distinguish clearly between outcomes and decision quality. A decision can be made well and still fail. A decision can be made poorly and still succeed.

If the PM conflates the two — "it worked out so I must have done it right" or "it failed so I must have gotten it wrong" — name that directly: "Whether this worked out is separate from whether it was a good decision. Let's focus on the process."


Calibration Notes

Audit the process, not the content. You're not second-guessing the actual call (cut the feature vs. keep it) — you're evaluating how the decision was reached and communicated. Stay in that lane.

Pressure matters. Many PM decisions are made under leadership pressure with imperfect data and too little time. Acknowledge that reality. The audit isn't about ideal conditions — it's about whether the PM exercised judgment within the constraints.

Push on the customer. The single most common PM failure mode in the source material is decisions that don't have a visible customer in them. If the PM can't articulate how the user was part of the reasoning, push on that first.

Reversibility is underused as a concept. Many PMs treat all decisions with the same urgency. Ask them to slow down on the ones that are hard to undo. If they didn't, name that.


Input/Output Contract

Accepts: A description of a specific PM decision (context, alternatives, outcome, communication)

Produces: Decision quality audit — what was done well, where the process broke down, and the one insight that matters most

Passes to: blind-spot-scan if the audit reveals a recurring pattern; terminal if the PM has specific improvements to apply to the next decision

© gnurio, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 1 other file (references) in skills/decision-audit of gnurio/nurijanian-skills.

  • SKILL.md
  • references/pm-excellence-behaviors.md

Open the folder on GitHubat commit 43a0566

Compare with similar skills

Decision 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.

Decision Audit compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Decision Audit this skillgnurio/nurijanian-skills124—~1.7kAutomated safety check: PassMIT
AuditorRaoFoundation/subtensor389—~813Automated safety check: PassApache-2.0
AuditorQinghongLin/data2story-skill156—~6.4kAutomated safety check: NotesMIT
AuditorQinghongLin/data2story-skill156—~917Automated safety check: NotesMIT
Indexing Issue Auditorsickn33/agentic-awesome-skills47k1 repos~1.5kAutomated safety check: PassMIT
Fda Food Safety Auditorsickn33/agentic-awesome-skills47k2 repos~759Automated safety check: PassMIT

Similar skills

  • Auditor

    RaoFoundation/subtensor

    Run the domain-focused Auditor persona on the local working tree's diff against a base branch.

    389 GitHub stars~813 tokensUpdated today
    DevelopmentAuto-check passed
  • Auditor

    QinghongLin/data2story-skill

    Audit a generated Data2Story blog for build correctness across ALL modalities by ACTUALLY RENDERING it in a real headless browser (when available) — catching blank/0-width charts, broken/oversized…

    156 GitHub stars~6.4k tokensUpdated 3 mo ago
    Productivity & AutomationAuto-check: notes
  • Auditor

    QinghongLin/data2story-skill

    Detect and fix layout issues in generated HTML using visual rendering tests.

    156 GitHub stars~917 tokensUpdated 3 mo ago
    Marketing & SEOAuto-check: notes
  • Indexing Issue Auditor

    sickn33/agentic-awesome-skills

    High-level technical SEO and site architecture auditor. An agent skill from sickn33/agentic-awesome-skills.

    47k GitHub starsUsed in 1 repo~1.5k tokens
    Marketing & SEOAuto-check passed
  • Fda Food Safety Auditor

    sickn33/agentic-awesome-skills

    Expert AI auditor for FDA Food Safety (FSMA), HACCP, and PCQI compliance.

    47k GitHub starsUsed in 2 repos~759 tokens
    Legal & ComplianceAuto-check passed
  • Fda Medtech Compliance Auditor

    sickn33/agentic-awesome-skills

    Expert AI auditor for Medical Device (SaMD) compliance, IEC 62304, and 21 CFR Part 820.

    47k GitHub starsUsed in 2 repos~818 tokens
    Legal & ComplianceAuto-check passed

More from gnurio/nurijanian-skills

All 15 skills in this repo
  • Vibe Code Leaf Finder

    gnurio/nurijanian-skills

    This skill should be used when a user wants to identify which parts of a codebase are safe to modify with AI ("vibe code") and which require careful human engineering.

    124 GitHub stars~1.9k tokensUpdated 1 mo ago
    Auto-check: notes
  • Corporate Misalignment Finder

    gnurio/nurijanian-skills

    Find, diagnose, and fix misalignment in corporate settings. An agent skill from gnurio/nurijanian-skills.

    124 GitHub stars~2.1k tokensUpdated 1 mo ago
    Auto-check passed
  • Verbalized Sampling

    gnurio/nurijanian-skills

    Generate diverse outputs by prompting for a probability distribution instead of a single response.

    124 GitHub stars~2k tokensUpdated 1 mo ago
    Auto-check: warnings
  • Focal Point Finder

    gnurio/nurijanian-skills

    This skill should be used when someone needs to find, propose, or evaluate a focal point in a coordination, negotiation, or alignment problem.

    124 GitHub stars~3.2k tokensUpdated 1 mo ago
    Auto-check passed
  • Orchestrate Pm Alignment

    gnurio/nurijanian-skills

    PM alignment coach and router. An agent skill from gnurio/nurijanian-skills.

    124 GitHub stars~1.5k tokensUpdated 1 mo ago
    Auto-check passed
  • Tech Sensemaking

    gnurio/nurijanian-skills

    Analyze technology announcements to surface non-obvious strategic implications using Verbalized Sampling.

    124 GitHub stars~1.8k tokensUpdated 1 mo ago
    Auto-check passed

Questions about Decision Audit

What does Decision Audit do?

PM decision quality auditor. An agent skill from gnurio/nurijanian-skills. Decision Audit is an agent skill from gnurio/nurijanian-skills. PM decision quality auditor.

When should I use Decision Audit?

Decision Audit fits situations like: A PM wants to audit a specific decision they made — not just whether it worked out; but whether it was a good decision by the criteria that define PM excellence; : was this the right call?; I want to audit this decision.

How do I install Decision Audit in Claude Code?

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

How do I install Decision Audit in Codex?

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

Can I use Decision 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 gnurio/nurijanian-skills --skill decision-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/decision-audit, .gemini/skills/decision-audit, .github/skills/decision-audit and .opencode/skills/decision-audit in your project.

What does Decision Audit need to run?

SKILL.md names no scripts, command-line tools or credentials: Decision Audit is instructions for the agent only.

Does Decision 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 Decision 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 Decision Audit use?

Decision Audit 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 Decision Audit use?

About 1.7k tokens (SKILL.md is roughly 7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 2.2k tokens, read only when the agent opens those files.

What are the alternatives to Decision Audit?

Skills that share tags, products or a category with Decision Audit: Auditor (RaoFoundation/subtensor, 389 stars), Auditor (QinghongLin/data2story-skill, 156 stars), Auditor (QinghongLin/data2story-skill, 156 stars) and Indexing Issue Auditor (sickn33/agentic-awesome-skills, 47k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Decision Audit?

gnurio (a GitHub user) maintains it in gnurio/nurijanian-skills, which has 124 GitHub stars. The repository holds 15 skills in this directory. The repository was last updated on August 13, 2026.

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