rpraharajrpraharaj/ai-sdlc/skills/update-raid/SKILL.md

update-raid

Skill0 starsChanged 16 days agoMITView on GitHub

Update the RAID log — risks, assumptions, issues, dependencies — from evidence. Use when the user asks to update RAID, add a risk, refresh assumptions, or /update-raid. Do not invent severity or green status.

In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- assess-changeSkill
- build-regression-packSkill
- charter-exploratorySkill
- classify-dataSkill
- commitSkill
- cut-releaseSkill
- data-changeSkill
- debugSkill
- design-experimentSkill
- diff-environmentsSkill
- draft-steercoSkill
- engineering-barSkill
- explain-codeSkill
- explore-codebaseSkill
- fix-ciSkill
- handoffSkill
- implement-changeSkill
- incident-triageSkill
- lean-reviewSkill
- map-dependenciesSkill
- map-design-handoffSkill
- map-processSkill
- open-prSkill
- performanceSkill
- plan-data-migrationSkill
- plan-incrementSkill
- plan-rollbackSkill
- plan-uatSkill
- prioritize-backlogSkill
- production-passSkill
- ready-to-mergeSkill
- record-decisionSkill
- refactor-safelySkill
- revert-changeSkill
- review-architectureSkill
- review-changeSkill
- review-pipelineSkill
- security-passSkill
- shape-workSkill
- ship-notesSkill
- spec-analyticsSkill
- spec-observabilitySkill
- start-projectSkill
- synthesize-discoverySkill
- triage-blockersSkill
- triage-defectSkill
- verify-uiSkill
- write-api-examplesSkill
- write-architectureSkill
- write-designSkill
- write-dev-tasksSkill
- write-docsSkill
- write-integration-contractSkill
- write-nfrSkill
- write-opportunitySkill
- write-prdSkill
- write-requirementsSkill
- write-runbookSkill
- The first 60 shown.

The file

We split this skill into the rules it gives an agent

8 rules. About 0 are common, 4 are distinctive, and 4 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.
4
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Very specific:
Keep one RAID file honest.
line 16
Distinctive:
Do not invent risks, owners, or dates.
line 18
Distinctive:
If the user says “add a risk that we might be late” with no evidence, record it as an assumption or stop and ask what would tell us it is …
line 35
Very specific:
Read AGENTS.md if present.
line 45
Very specific:
Read docs/govern/raid.md if it exists.
line 46
Distinctive:
Add or update only items with a source.
line 48
Distinctive:
Do not change owner, severity, or status to closed unless the user said so.
line 49
Very specific:
After edits, write-status may run — do not write status inside this file beyond the item list.
line 51

≈ “Common” is an estimate: at least 1 in 5 of the 350,495 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.

Keep what fits and drop the rest. Your version, ready for your agents.

Files

SKILL.md

Update RAID

Keep one RAID file honest. This is not a steerco deck (draft-steerco), not a weekly status (write-status), and not a change request (assess-change).

Do not invent risks, owners, or dates. Do not delete an open item without a human.

Is this the right skill?

Signal	Do this instead
One-page RAG for this week	`write-status` (read this RAID)
Scope/date/design change impact	`assess-change`
Steerco paper	`draft-steerco`
Cross-team contract map	`map-dependencies`

Required inputs

Existing docs/govern/raid.md if it exists (create from the template if not)
Evidence: named artifact, ticket id, git fact, or CI result
context/decision-rights.md if it exists (for escalation)

If the user says “add a risk that we might be late” with no evidence, record it as an assumption or stop and ask what would tell us it is true.

Human decisions (do not invent)

Severity and owner
Closing an item
Date commitments

Procedure

Read AGENTS.md if present. Read context/decision-rights.md if present.
Read docs/govern/raid.md if it exists. If not, offer to create docs/govern/ and start from references/raid-template.md.
Open the template only to keep every heading. Do not drop columns.
Add or update only items with a source. Source = path, ticket id, or “user: <name>”.
Do not change owner, severity, or status to closed unless the user said so.
Dependencies name the other team or system from context/systems-of-record.md when possible.
After edits, write-status may run — do not write status inside this file beyond the item list.

Output

Path: docs/govern/raid.md (one file, updated in place)
Template: references/raid-template.md

Quality bar

Every new or changed row has a source
No closed item without a human
No invented date or owner (unassigned is allowed)
Headings from the template remain
Secrets are absent

Done

Path
Counts: open risks / assumptions / issues / dependencies
Next skill: write-status or assess-change if an item is a scope change

Download now (ZIP)

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

What did you use it for? e.g. Reviewing pull requests in a Rails app

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.

Check your setup, free