sow-review
Skill4 starsChanged 36 days agoMITView on GitHub
Review a Statement of Work for scope risks, ambiguous language, missing protections, and negotiation points. Use before signing or whenever a client sends a new or revised SOW. Usage - /sow-review path/to/sow.md
1 other project uses a version of this.
Adopted by
Most recently taken up by
- hajarlachheb/claude-skillstheir own version, first seen Nov 16, 2026
Other versions1 project uses a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 1
- hajarlachheb/claude-skills★ 0same name
How matches are found. Word for word: the exact same text. Edited: shares passages with this file (“99% same” means 99% of its five-word phrases also appear here; 10% or more counts). Their own version: similar meaning, or, weakest, the same name. We can’t tell which project had it first. Projects are counted among the 200 most-starred candidates, and mentions are links to the repository we found, up to 50 per site, so both counts are a floor.
In this repository11 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- change-requestSkill
- code-review-lightSkill
- deliverable-qaSkill
- exec-summarySkill
- meeting-prepSkill
- stakeholder-prepSkill
- status-commsSkill
- status-reportSkill
- transcript-actionsSkill
- weekly-briefSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 4 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 20
If no path was given, ask for one.
- Distinctive: line 24
Read the full document first.
- Distinctive: line 55
Use direct, practical language.
- Distinctive: line 66
Add an Acceptance Criteria section specifying test pass rates and sign-off process
≈ “Common” is an estimate: at least 1 in 5 of the 372,429 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
SOW Review
Review a Statement of Work for scope risks, ambiguous language, missing protections, and negotiation opportunities. Best run before signatures, not after.
Input
$ARGUMENTS is the path to the SOW (.md, .txt, .docx, or .pdf), optionally followed by
context after --, for example:
/sow-review my-projects/client/sow.md -- fixed-price, client wants to start in 3 weeksIf no path was given, ask for one. Do not review from memory of an earlier conversation.
Steps
Read the full document first. Then assess it across the dimensions below and produce the structured output. Quote the document's own words wherever you flag a risk, with the section number, so the reader can find it.
Output
Overall Risk Rating: [🔴 High / 🟡 Medium / 🟢 Low]: one-sentence summary
Scope Risks:
- Ambiguous deliverables, undefined acceptance criteria, or scope that could "expand by interpretation"
- Quote the specific language and explain the risk
Commercial Risks:
- Pricing assumptions that may not hold, payment terms, penalty clauses, IP ownership, limitation of liability gaps
Timeline Risks:
- Aggressive milestones, dependencies on client actions not contractually required, holidays or blackout periods unaccounted for
Assumptions & Exclusions:
- List any assumptions that shift risk to the client. Are they explicit and strong enough?
- Flag any missing exclusions that should be there
Change Control:
- Is there a defined change control process? What triggers it? Who approves?
Recommended Negotiation Points:
- Top 3 to 5 specific changes to request before signing, with suggested replacement language
What I did not check: one or two lines naming anything the review could not assess from the document alone (for example, whether the rate card matches the firm's standard).
Use direct, practical language. This review is for the delivery lead, not the client. The negotiation is the lead's to run; this review is the preparation.
Example Output
Overall Risk Rating: 🔴 High. Acceptance criteria are undefined and the change control section is absent.
Scope Risks:
- "The team will deliver a fully functional data warehouse" (Section 2.1). "Fully functional" is undefined. Recommend replacing with a specific list of deliverables and a signed acceptance checklist.
Recommended Negotiation Points:
- Add an Acceptance Criteria section specifying test pass rates and sign-off process
- Insert a Change Control clause (the
/change-requestskill has a template) - Clarify client responsibilities for data access and SME availability (currently missing)
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

