Archive
Persist session learnings, bug fixes, and deploy notes under `.archive/YYYY-MM-DD/` with tagged markdown and a searchable `.archive/MEMORY.md` index for the next agent run.
Overview
Archive is a journey-wide agent skill that captures debugging, deploy, and task learnings into `.archive/` markdown and a MEMORY index—usable whenever a solo builder needs durable session memory before repeating work.
Install
npx skills add https://github.com/resciencelab/opc-skills --skill archiveWhat is this skill?
- Writes dated folders `.archive/yyyy-mm-dd/` with indexed markdown and searchable tags
- Maintains `.archive/MEMORY.md` one-line category index for cross-session lookup
- Lookup workflow: grep archives and read MEMORY before infra, deploy, or CI repeats
- YAML frontmatter template with optional `related` links to prior archives
- Triggers on deploy completion, hard bugs, multi-step learnings, or user says archive this
- `.archive/YYYY-MM-DD/` dated directories
- `.archive/MEMORY.md` category index
Adoption & trust: 839 installs on skills.sh; 920 GitHub stars; 3/3 security scanners passed (skills.sh audits).
What problem does it solve?
You solved a deploy or CI issue last week but the next agent session has no indexed, searchable record inside the repo.
Who is it for?
Indie devs running long-horizon repos with Claude Code or Cursor who lose tribal knowledge between sessions.
Skip if: One-line fixes with no reuse value, or teams that already mandate an external wiki with strict compliance workflows.
When should I use this skill?
When completing a significant task, resolving a tricky bug, deploying, or when the user says archive this; consult archives before infra, deploy, or CI work.
What do I get? / Deliverables
Dated archive files and an updated MEMORY.md give you grep-ready context before debugging infrastructure or rerunning multi-step processes.
- Dated archive markdown with tags
- Updated `.archive/MEMORY.md` index
Recommended Skills
Journey fit
Useful at every journey phase - explore requirements and options before committing to a direction.
Where it fits
After fixing a recurring queue worker crash, archive root cause and grep keywords for the next on-call-style session.
Post-migration, write dated notes and link related archives so the docs subphase stays tied to lived implementation history.
Log first production deploy steps and rollback quirks before scaling launch traffic.
Archive spike conclusions so Validate does not rerun discarded experiments in full Build.
Index support-related fixes that affect customer-facing behavior for faster lifecycle responses.
How it compares
Repo-local indexed archives—not a cloud note app or generic git commit message discipline alone.
Common Questions / FAQ
Who is archive for?
Solo and indie builders who want agent sessions to read prior deploy, debug, and process learnings from `.archive/` before touching infra or CI again.
When should I use archive?
After ship-worthy tasks in Build, when Operate debugging resolves a tricky bug, before Validate when repeating a prior prototype path, or any time you say archive this—consult MEMORY first when similar errors reappear.
Is archive safe to install?
It writes markdown under your repo only—avoid storing secrets in archive bodies; review the Security Audits panel on this Prism page for the opc-skills package.
SKILL.md
READMESKILL.md - Archive
# Archive Skill Capture, index, and reuse project knowledge across sessions. ## When to Archive - After completing a significant task (deploy, migration, major feature) - After resolving a tricky debugging session - When the user says "archive this" - After any multi-step process with learnings worth preserving ## When to Consult Archives - Before debugging infrastructure, deploy, or CI issues - Before repeating a process done in a past session - When encountering an error that may have been solved before **Search**: `grep -ri "keyword" .archive/` **Index**: `.archive/MEMORY.md` ## Archive Workflow 1. Read `.archive/MEMORY.md` — check for related existing archives 2. Create `.archive/YYYY-MM-DD/` directory if needed 3. Write markdown file with YAML frontmatter (see `references/TEMPLATE.md`) 4. **Update `.archive/MEMORY.md`**: add one-line entry under the right category 5. If related archives exist, add `related` field in frontmatter ## Lookup Workflow 1. Read `.archive/MEMORY.md` to find relevant entries 2. Read the specific archive file for detailed context 3. Apply learnings to current task ## Categories - **infrastructure** — AWS, ECS, IAM, networking, secrets, CloudWatch - **release** — TestFlight, versioning, Git Flow, CHANGELOG - **debugging** — Bug fixes, error resolution, gotchas - **feature** — Feature design, implementation notes - **design** — UI/UX, icons, visual design ## Rules - `.archive/` must be in `.gitignore` — local-only notes - Keep entries concise but reproducible - Focus on **problems, fixes, and exact commands** - Always update MEMORY.md after creating an archive - Use descriptive filenames (e.g., `cloudwatch-logging.md` not `session.md`) - Include YAML frontmatter with `tags`, `category`, and optional `related`