risk-review
Skill1 starsChanged 19 days agoMITView on GitHub
Surface project risks not yet captured in the memory bank. Use when the user asks for risk review, hidden risks, assumptions, unknowns, or pre-planning risk assessment.
2 other projects use a version of this.
Adopted by
Most recently taken up by
- tyabu12/claude-kittheir own version, first seen Oct 20, 2026
- ddlaws0n/customer-success-skillstheir own version, first seen Sep 13, 2026
Other versions2 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 2
- ddlaws0n/customer-success-skills★ 0same name
- tyabu12/claude-kit★ 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 repository36 other files it gives its agents.
- AGENTS.mdAGENTS.md
- analyzeSkill
- ask-claudeSkill
- breakdownSkill
- decision-logSkill
- discoverSkill
- from-prdSkill
- handoffSkill
- init-memorySkill
- retroSkill
- reviewSkill
- runbookSkill
- security-checkSkill
- shipSkill
- startSkill
- sync-upstreamSkill
- update-memorySkill
- weekly-updateSkill
- analyzeSkill
- ask-codexSkill
- breakdownSkill
- decision-logSkill
- discoverSkill
- from-prdSkill
- handoffSkill
- init-memorySkill
- retroSkill
- reviewSkill
- risk-reviewSkill
- runbookSkill
- security-checkSkill
- shipSkill
- startSkill
- sync-upstreamSkill
- update-memorySkill
- weekly-updateSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 2 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈2
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Very specific: line 10
Effective bank: if memory-bank.local/ exists (upstream Serel Memory development only), all memory-bank and .rules reads and writes below …
- Distinctive: line 56
Don't manufacture risks. If a category has nothing real, say so explicitly.
- Distinctive: line 57
If a risk is genuinely "out of our control," still name it — visibility matters even when action doesn't.
- Very specific: line 59
After the review, ask the user which risks belong in memory-bank/activeContext.md, memory-bank/progress.md, or memory-bank/decisionLog.md, …
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
Risk Review
Surface risks and unknowns that aren't already captured in the memory bank. The goal is to find what could derail this project that nobody's named yet. Do not invent risks just to fill categories.
Effective bank: if memory-bank.local/ exists (upstream Serel Memory development only), all memory-bank and .rules reads and writes below target it instead of the tracked templates; skip files it doesn't contain. See "Resolving the effective bank" in docs/workflow-contract.md.
Scope: resolve which bank this targets per "Resolving scope" in docs/workflow-contract.md — an optional --scope <path> argument selects a project bank when the repo configures scopes; otherwise the root bank, as always.
Workflow
- Read:
memory-bank/projectbrief.md— goals and success criteriamemory-bank/productContext.md— user/UX contextmemory-bank/systemPatterns.md— architectural decisions and assumptionsmemory-bank/techContext.md— stack, dependencies, constraintsmemory-bank/decisionLog.md— durable decisions and ADR referencesmemory-bank/activeContext.md— current focusmemory-bank/progress.md— status and known issues.rules— any documented gotchas or rejected approaches
- Inspect relevant code, docs, dependency manifests, recent commits, or open diffs when needed.
- Identify risks across these categories:
- Technical: dependencies, scaling, architecture decisions that might not survive contact with reality
- Schedule: dates, milestones, anything time-bound
- External/vendor: vendors, APIs, integrations, anything outside the team's control
- Resource/capacity: people, budget, capacity
- Scope: ambiguity in requirements, scope creep, feature inflation
- Operational/security: deployment, monitoring, on-call coverage, security
- Assumptions: things the project assumes are true that might not be
- Rank by likelihood times impact, highest combined likelihood × impact first.
Output
For each risk:
## [Short name]
- Category: [from above]
- What could go wrong: [specific failure mode]
- Likelihood: high / medium / low
- Impact if it hits: [concrete consequence]
- Mitigation: [what we could do now to reduce likelihood or impact]
- Status: undocumented / partially documented / documented but staleOutput a ranked list, highest combined likelihood × impact first.
Rules
- Surface NEW risks. Don't just restate what's already in
progress.mdunder "known issues." - Be specific. "API might be slow" is not a risk; "Vendor X's rate limit is 100 req/min and we're projecting 300 req/min at launch" is.
- Don't manufacture risks. If a category has nothing real, say so explicitly.
- If a risk is genuinely "out of our control," still name it — visibility matters even when action doesn't.
After the review, ask the user which risks belong in memory-bank/activeContext.md, memory-bank/progress.md, or memory-bank/decisionLog.md, and add them with confirmation. Do not write memory updates without confirmation.
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.

