
stakeholder-review
Use when a deliverable needs structured stakeholder sign-off before finalization—runs the pre-read, feedback-type alignment, and conflict-resolution protocol.
- Installs
- 43
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://github.com/joellewis/skill-library --skill stakeholder-review- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads stakeholder-review automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Overview
Stakeholder-review is the "Group IQ" gate that ensures deliverables are stress-tested by the organizational ecosystem before finalization. It moves feedback from a friction-filled "push" (giving) to a high-value "pull" (seeking), focusing on alignment, safety, and clear resolution of conflicting inputs.
Iron Law
NO FINAL VERSION WITHOUT DOCUMENTED STAKEHOLDER FEEDBACK AND RESOLUTION
Violating this law leads to "shadow vetoes" later in the process, misalignment on success metrics, and the exclusion of critical cross-functional insights that improve the Group IQ.
State Machine
digraph stakeholder_review_flow {
"Deliverable Drafted" [shape=doublecircle];
"Step 1: Prepare Pre-read" [shape=box];
"Step 2: Align Purpose" [shape=box];
"Step 3: Review Session" [shape=box];
"Gate: Resolution" [shape=diamond];
"Step 4: Close the Loop" [shape=box];
"Final Version Approved" [shape=doublecircle];
"Deliverable Drafted" -> "Step 1: Prepare Pre-read";
"Step 1: Prepare Pre-read" -> "Step 2: Align Purpose";
"Step 2: Align Purpose" -> "Step 3: Review Session";
"Step 3: Review Session" -> "Gate: Resolution";
"Gate: Resolution" -> "Step 1: Prepare Pre-read" [label="revise"];
"Gate: Resolution" -> "Step 4: Close the Loop" [label="resolved"];
"Step 4: Close the Loop" -> "Final Version Approved";
}
When to Use This Skill
- Before finalizing high-stakes documents (PRDs, Strategy Memos, Pitch Decks).
- When a project involves multiple cross-functional dependencies.
- During Quarterly Business Reviews (QBRs) or project post-mortems.
- When you notice "silence" or "violence" in response to a proposal.
When NOT to Use This Skill
- For low-stakes, iterative internal team updates.
- For pure brainstorming sessions (use
problem-framinginstead). - When seeking emotional support rather than technical or strategic critique.
Core Process
Step 1: Prepare the Pre-read
- Distill the Narrative: Draft a concise (roughly 5-page) document or presentation that covers both backward-looking metrics and forward-looking goals. (Source: Johnson, Scaling People)
- Advance Distribution: Share the document 24-48 hours before the meeting. If no pre-read occurred, dedicate the first 15-20 minutes of the session to silent reading. (Source: Johnson, Scaling People)
Step 2: Align the Purpose
- Label the Feedback Type: Explicitly state whether you are seeking Appreciation (acknowledgment), Coaching (advice to improve), or Evaluation (assessment against standards). (Source: Stone, Thanks for the Feedback)
- Negotiate Expectations: Check in: "I'm looking for coaching on the strategy. Is that what you prepared to give?" This prevents "cross-transactions" where one party gives evaluation when the other wants coaching. (Source: Stone, Thanks for the Feedback)
Step 3: Conduct the Review Session
- Swap "Feedback" for "Advice": Ask "What advice do you have?" rather than "Do you have feedback?" This lowers social friction and attracts more actionable input. (Source: First Round Review, Berry)
- Look Together, Not Oppositional: Stand "next to" the stakeholder to look at the work together. Use "Go Meta" tactics: "It feels like we're not talking about the big issue. Is there a challenge here we're avoiding?" (Source: Johnson, Scaling People)
- Maintain Safety: If stakeholders move to silence or violence, step out of the content and restore safety using Mutual Purpose and Mutual Respect. (Source: Grenny, Crucial Conversations)
Step 4: Close the Loop
- Document Decisions: Record notes with explicit decisions and next steps. (Source: Johnson, Scaling People)
- Share the Action Plan: Distribute a summary of the feedback received and how it will be resolved. "Closing the loop" gets stakeholders invested in the final outcome. (Source: First Round Review, Berry)
Cross-Skill Invocations
REQUIRED SUB-SKILL: stakeholder-discovery — To ensure the right people are in the room.
RECOMMENDED SUB-SKILL: assumption-audit — To validate claims raised during the review.
RECOMMENDED SUB-SKILL: feedback-coach — To manage difficult interpersonal dynamics during the session.
Rationalization Table
| Thought | Reality |
|---|---|
| "I'll just get approval over Slack/email." | Asynchronous feedback lacks the "Group IQ" and nuance of a live, structured review. |
| "The stakeholders are too busy for a meeting." | Skipping the gate now leads to expensive rework or late-stage "shadow vetoes." |
| "I'll talk to them once the version is finished." | This is too late. The iron law requires feedback before finalization to be effective. |
| "I already know what they're going to say." | Confirmation bias blinds you to the 10% of feedback that is often critical for success. |
Red Flags
These thoughts mean STOP — you are about to shortcut:
- "This is just a formality to check a box." → You are ignoring the "Group IQ" value.
- "I'll filter their feedback before the team hears it." → You are compromising transparency and trust.
- "I'm preparing my defense while they are still talking." → You have triggered a "Truth Trigger" and are no longer listening.
Diagnostic Checklist
- Has a pre-read been distributed at least 24 hours in advance?
- Have we explicitly agreed on the type of feedback (Appreciation, Coaching, Evaluation) being sought?
- Are we using "Advice" language to lower friction?
- Is there a dedicated scribe recording decisions and next steps?
- Has the "elephant in the room" (the thing you think you cannot say) been named?
Sources
- Johnson, Scaling People, Ch. 2 & 5 — QBRs, pre-read culture, and internal comms.
- Stone & Heen, Thanks for the Feedback, Ch. 2 & 3 — Feedback triad and purpose alignment.
- Grenny et al., Crucial Conversations, Ch. 5 — Safety and Mutual Purpose.
- First Round Review, "The Best Leaders are Feedback Magnets" — Advice vs. Feedback and closing the loop.
FAQ
What does the stakeholder-review skill do?
Use when a deliverable needs structured stakeholder sign-off before finalization—runs the pre-read, feedback-type alignment, and conflict-resolution protocol.
How do I install stakeholder-review?
Run npx skills add https://github.com/joellewis/skill-library --skill stakeholder-review in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/stakeholder-review/ (personal) or .claude/skills/stakeholder-review/ (project).
Which AI agents can use stakeholder-review?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is stakeholder-review safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains stakeholder-review?
It is published by joellewis in joellewis/skill-library. It has 43 recorded installs.
More from joellewis/skill-library
fiction-architect
joellewis/skill-library
Designs plot structure and story arcs using McKee's value turns, Campbell's monomyth, and Sanderson's Promise/Progress/Payoff model to ensure causal integrity and emotional resonance. Use when constructing narratives, outlining novels, or diagnosing why a story feels broken.
dialogue-craft
joellewis/skill-library
Writes and refines dialogue that serves plot and reveals character through subtext, intention, and behavioral exchange — applying McKee's subtext principle and Sorkin's intention-and-obstacle model. Use when dialogue feels flat, expository, or 'on the nose.'
world-building-logic
joellewis/skill-library
Engineers internally consistent fictional worlds using Brand's Pace Layers for social structure and Sanderson's Laws of Magic for system constraints. Use when building settings, designing magic or tech systems, or auditing a world for logical contradictions.
problem-framing
joellewis/skill-library
Use when beginning analytical or strategic tasks, facing undefined problems, or facing analysis paralysis—requires explicit problem definition before proceeding.
character-vulnerability
joellewis/skill-library
Use when a character feels flat, too competent, or unrelatable—identifies the Sacred Flaw (Storr's Theory of Control) and dials the Three Sliders (Sanderson) to create earned vulnerability.
one-pager
joellewis/skill-library
Use when compressing a complex strategy or analysis into a strictly one-page narrative—enforces Pyramid SCQ structure and Orwell word-budget discipline.
Popular code quality & workflow skills
grill-me
mattpocock/skills
A relentless interview to sharpen a plan or design.
improve-codebase-architecture
mattpocock/skills
Scan a codebase for deepening opportunities, present them as a visual HTML report, then grill through whichever one you pick.
handoff
mattpocock/skills
Compact the current conversation into a handoff document for another agent to pick up.
domain-modeling
mattpocock/skills
Build and sharpen a project's domain model. Use when discussing codebase terminology, writing or editing a GLOSSARY.md, or recording or editing an ADR.
codebase-design
mattpocock/skills
Shared vocabulary for designing deep modules. Use when the user wants to design or improve a module's interface, find deepening opportunities, decide where a seam goes, make code more testable or AI-navigable, or when another skill needs the deep-module vocabulary.
diagnosing-bugs
mattpocock/skills
Diagnosis loop for hard bugs and performance regressions. Use when the user says "diagnose"/"debug this", or reports something broken/throwing/failing/slow.