
Memory Ci Capture
- 286 installs
- 3.6k repo stars
- Updated August 5, 2026
- basicmachines-co/basic-memory
memory-ci-capture is a Claude skill that synthesizes GitHub delivery context in CI into structured AgentSynthesis JSON for a Basic Memory project update.
About
This skill runs in CI after `bm ci collect` prepares a ProjectUpdateContext, turning a GitHub delivery moment such as a merged PR or production deploy into a concise Basic Memory project update. It returns only structured AgentSynthesis JSON for `bm ci publish` and never invents tests, checks, or decisions. It records what changed and why for future humans and agents.
- Synthesizes a GitHub delivery moment (merged PR, prod deploy) into a Basic Memory project update
- Reads the immutable ProjectUpdateContext produced by `bm ci collect` and returns only AgentSynthesis JSON
- Does not invent tests, deploy checks, or decisions; absent evidence is left empty
Memory Ci Capture by the numbers
- 286 all-time installs (skills.sh)
- Ranked #341 of 1,435 DevOps & CI/CD skills by installs in the Skillselion catalog
- Data as of Aug 5, 2026 (Skillselion catalog sync)
memory-ci-capture capabilities & compatibility
- Capabilities
- ci capture · release notes · delivery summary
- Works with
- github
- Use cases
- ci cd · documentation · memory
What memory-ci-capture says it does
GitHub records the mechanics. Basic Memory remembers what changed and why.
Do not invent tests, deploy checks, linked issues, product impact, or decisions.
npx skills add https://github.com/basicmachines-co/basic-memory --skill memory-ci-captureAdd your badge
Show developers this skill is listed on Skillselion. Paste this into your README.
| Installs | 286 |
|---|---|
| repo stars | ★ 3.6k |
| Last updated | August 5, 2026 |
| Repository | basicmachines-co/basic-memory ↗ |
What it does
Synthesize a GitHub merge or deploy into a structured Basic Memory project update in CI.
Who is it for?
Turning a merged PR or production deploy into a factual, evidence-only project memory update inside CI.
Skip if: Inventing tests, deploy checks, linked issues, or decisions not present in the context.
When should I use this skill?
In CI after `bm ci collect` prepares a ProjectUpdateContext for a delivery moment.
What you get
Structured AgentSynthesis JSON summarizing what changed and why, ready for `bm ci publish`.
- AgentSynthesis JSON project update
By the numbers
- 8-field AgentSynthesis output shape
Files
Memory CI Capture
Turn a meaningful GitHub delivery moment into project memory. GitHub records the mechanics. Basic Memory remembers what changed and why.
Inputs
Read the ProjectUpdateContext JSON produced by bm ci collect at .github/basic-memory/project-update-context.json. Treat it as the immutable source of truth for repository, event type, PR number, workflow run, SHA, source URL, timestamps, and deployment environment.
Do not invent tests, deploy checks, linked issues, product impact, or decisions. If evidence is absent, say so briefly in verification or leave the field empty.
Output
Return only JSON matching the AgentSynthesis shape:
{
"summary": "What changed.",
"why_it_matters": "Why this update matters for future humans and agents.",
"user_facing_changes": [],
"internal_changes": [],
"verification": [],
"follow_ups": [],
"decision_candidates": [],
"task_candidates": []
}Synthesis Rules
- Prefer a short explanation over a commit-by-commit changelog.
- Preserve intent, changed behavior, source links, verification evidence present
in the context, and concrete follow-ups.
- Put explicit product or architecture decisions in
decision_candidatesonly
when the source context clearly contains them.
- Put future work in
task_candidatesonly when it is concrete enough to act on. - Keep the tone factual and useful. This is project memory, not marketing copy.
Event Guidance
For merged pull requests, focus on why the PR existed, what area changed, what issues it advanced or closed, and what verification evidence appears in the context.
For production deploys, focus on what reached production, the deployed SHA, environment, workflow run, and verification evidence. Do not overclaim success beyond the workflow and source facts.
Related skills
FAQ
What does it output?
Only JSON matching the AgentSynthesis shape for bm ci publish, with fields like summary, why_it_matters, and verification.
Can it claim tests passed?
No. It must not invent tests, deploy checks, or decisions; absent evidence is left empty or noted briefly.