change-impact
Skill1 starsChanged 54 days agoMITView on GitHub
Propagate an upstream Artifact, Contract, decision, assumption, dependency, or code change through downstream dependencies, mark evidence stale or unverified, and define revalidation. Use whenever a validated basis changes.
6 other projects use a version of this.
Adopted by
Most recently taken up by
- marinvch/Cortextheir own version, first seen Nov 1, 2026
- willgt-oss/willgt-skillstheir own version, first seen Nov 1, 2026
- Nomanriaz786/claude-consulting-teamtheir own version, first seen Nov 1, 2026
- kimgea/agent-kittheir own version, first seen Oct 15, 2026
- Seekers2001/docs-governancetheir own version, first seen Oct 13, 2026
- qshanx/docs-governancetheir own version, first seen Oct 13, 2026
Other versions6 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 6
- Seekers2001/docs-governance★ 320same name
- qshanx/docs-governance★ 253same name
- marinvch/Cortex★ 1same name
- Nomanriaz786/claude-consulting-team★ 1same name
- kimgea/agent-kit★ 0same name
- willgt-oss/willgt-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 repository21 other files it gives its agents.
- CLAUDE.mdCLAUDE.md
- adaptive-testingSkill
- architecture-decisionSkill
- artifact-validationSkill
- clarification-gateSkill
- code-reviewSkill
- component-planningSkill
- failure-diagnosisSkill
- failure-escalationSkill
- framework-checkpointSkill
- framework-resumeSkill
- gap-analysisSkill
- implement-componentSkill
- integration-gateSkill
- minimum-pathSkill
- project-intakeSkill
- quality-gateSkill
- reverse-engineeringSkill
- stage-gateSkill
- traceabilitySkill
- workflow-assessmentSkill
The file
We split this skill into the rules it gives an agent
7 rules. 0 are common, 5 are distinctive, and 2 are very specific to this project.
0
Common
Most of the 4 edited versions we read keep these.
5
Distinctive
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 14
Run after any relevant upstream revision, disproven assumption, changed decision, Contract/schema/API change, dependency upgrade, or code …
- Distinctive: line 37
Update risks, assumptions, decisions, Artifact Registry, Component State, and traceability.
- Distinctive: line 38
Run Gap Analysis and recompute the Minimum Necessary Path.
- Distinctive: line 43
Do not invalidate the whole project when bounded consumers are identifiable.
- Very specific: line 44
Do not retain VALID or STABLE when its validation basis changed materially.
- Distinctive: line 64
Use Reverse Engineering/Traceability to recover missing links, Clarification Gate for changed intent, Architecture Decision for structural …
- Distinctive: line 68
Stop when affected and unaffected scope, state changes, and revalidation path are explicit, or when missing evidence blocks safe bounding.
“Common” is measured: kept by at least 6 in 10 of the 4 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
Change Impact
Purpose
Invalidate only affected downstream work, preserve unaffected valid work, and trigger a new Minimum Necessary Path.
Trigger
Run after any relevant upstream revision, disproven assumption, changed decision, Contract/schema/API change, dependency upgrade, or code modification to a stable Component.
Inputs
- Changed item and old/new revisions, reason, effective decision, and changed semantics.
- Artifact dependency graph, traceability links, Component Graph, Contracts, and current State.
- Existing validation/Gate evidence, target, Workflow Level, and current Minimum Necessary Path.
Prerequisites
- Identify the exact changed revision and avoid treating formatting-only edits as semantic changes without evidence.
- Preserve prior evidence as history.
Procedure
- Compare old and new revisions and describe semantic, interface, behavior, data, constraint, or evidence changes.
- Locate direct downstream consumers through dependencies, Contracts, traceability, and code/test references.
- Traverse transitively only while the changed semantics can affect the consumer.
- For each affected Artifact, record the reason and mark
STALEunless evidence already proves invalidity. - For affected
STABLEComponents, markUNVERIFIED; setFAILEDonly when current evidence demonstrates failure. - Invalidate revision-specific test, review, integration, and Gate evidence as needed.
- Identify unaffected scope and record why its evidence remains valid.
- Define supplement, revalidation, repair, regeneration, testing, review, and integration scope.
- Update risks, assumptions, decisions, Artifact Registry, Component State, and traceability.
- Run Gap Analysis and recompute the Minimum Necessary Path.
Decision Rules
- Dependence alone does not prove impact; record the semantic propagation path.
- Do not invalidate the whole project when bounded consumers are identifiable.
- Do not retain
VALIDorSTABLEwhen its validation basis changed materially. - Contract compatibility evidence can bound impact but must match exact versions.
- A code edit always invalidates affected Component verification even if behavior is intended to remain unchanged.
Outputs
- Impact Set with changed source, downstream paths, affected revisions, and rationale.
- Updated
STALE,UNVERIFIED, orFAILEDstates. - Unaffected set with preservation rationale.
- Revalidation/rework plan and Minimum Path recomputation trigger.
Failure Cases
- Dependency or traceability links are missing.
- Old/new revisions cannot be identified.
- Change semantics are ambiguous.
- Impact crosses an undocumented shared resource or runtime boundary.
Escalation
Use Reverse Engineering/Traceability to recover missing links, Clarification Gate for changed intent, Architecture Decision for structural consequences, and Workflow Assessment when blast radius increases.
Stop Conditions
Stop when affected and unaffected scope, state changes, and revalidation path are explicit, or when missing evidence blocks safe bounding. Do not execute all rework in this Skill.
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.

