rpraharajrpraharaj/ai-sdlc/skills/assess-change/SKILL.md

assess-change

Skill0 starsChanged 18 days agoMITView on GitHub

Assess impact of a scope, date, or design change against current artifacts. Use when the user asks for a change request, impact assessment, re-plan, or /assess-change. Do not accept the change. Do not invent capacity or dates.

In this repository66 other files it gives its agents.
- AGENTS.mdAGENTS.md
- a11y-passSkill
- 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
- update-raidSkill
- 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

6 rules. About 0 are common, 4 are distinctive, and 2 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.
2
Very specific
Tied to their project's names, files or tools. Probably skip.

Common
Distinctive
Very specific

Distinctive:
Do not implement. Do not treat the change as accepted.
line 19
Distinctive:
If there is no baseline artifact, stop.
line 36
Distinctive:
Must vs Should if scope moves
line 42
Very specific:
Read AGENTS.md if present.
line 46
Distinctive:
Read the baseline artifacts the user named (PRD, requirements, plan, RAID, contracts).
line 47
Very specific:
After the human decides, next is update-raid and, if accepted, the skill that updates the moved artifact (write-requirements, write-prd, …).
line 56

≈ “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

Assess change

Show what breaks if we say yes. This is not status (write-status), not RAID (update-raid — update RAID after the human decides), and not a new PRD.

Do not implement. Do not treat the change as accepted.

Is this the right skill?

Signal	Do this instead
New problem, no current plan	`write-opportunity` / `write-prd`
Weekly RAG	`write-status`
Add a risk without a proposed change	`update-raid`
Technical design of the new shape	`write-design` after a human accepts

Required inputs

The proposed change in one paragraph (from the user)
The current baseline: PRD and/or plan and/or RAID — at least one path
context/decision-rights.md (who may accept)

If there is no baseline artifact, stop. You cannot assess impact against a blank.

Human decisions (do not invent)

Accept, accept-with-conditions, or reject
New date or budget
Must vs Should if scope moves

Procedure

Read AGENTS.md if present. Read context/decision-rights.md if present.
Read the baseline artifacts the user named (PRD, requirements, plan, RAID, contracts).
Find the home: docs/govern/change-YYYY-MM-DD-<slug>.md.
Open references/change-template.md. Copy every heading. Write n/a when unused.
List impacts only where you can name a file or RAID id:
- scope (requirements that move)
- date (only if a date already exists — do not invent a new one)
- contracts / NFR / UAT
- teams (from process map or systems-of-record)
Options: at least accept as asked, smaller alternative, reject. Recommendation is allowed; decision stays unassigned.
After the human decides, next is update-raid and, if accepted, the skill that updates the moved artifact (write-requirements, write-prd, …).

Output

Path: docs/govern/change-YYYY-MM-DD-<slug>.md
Template: references/change-template.md

Quality bar

Baseline paths are named
Every impact cites a file or RAID id
Three options exist, including reject
Decision is unassigned unless the user already decided
No invented date or headcount
Unused headings are n/a

Done

Path
Impact count
Next: human decision, then update-raid and the skill for the moved artifact

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