How do I install the Persisting Bigpicture Learnings skill?

Run npx skillmds@latest add qte77/persisting-bigpicture-learnings in your terminal (requires Node.js), paste this page's agent-chat prompt into Claude, Cursor, or any MCP-connected agent, or download the SKILL.md file and copy it into your agent's skills directory.

What does the Persisting Bigpicture Learnings skill do?

Persist Bigpicture to Learnings Hub It is listed under Coding & Dev Tools on SkillMD.

Is Persisting Bigpicture Learnings safe to use?

This skill has not completed SkillMD's automated safety review yet. SkillMD never runs a skill's scripts for you; review the SKILL.md before installing.

Which AI agents work with Persisting Bigpicture Learnings?

This skill is tagged as working with Claude Code, Claude.ai, OpenAI Codex. SKILL.md is an open format, so most agents that read a skills directory can load it too.

Is Persisting Bigpicture Learnings free to use?

Yes. Installing skills from SkillMD is free, and the skill stays under its author's original license.

Who published Persisting Bigpicture Learnings?

qte77 (@qte77) published this skill. Their other Agent Skills are listed on their SkillMD profile.

Persisting Bigpicture Learnings by qte77

Name: Persisting Bigpicture Learnings
Author: qte77

File contents

Persist Bigpicture to Learnings Hub

Target: $ARGUMENTS

Persists the output of /synthesizing-cc-bigpicture as a dated snapshot in a learnings hub. Maintains a latest.md pointer (always current) and an append-only archive for compound cross-session learning.

Arguments

Position	Name	Required	Default	Description
1	`input-path`	no	`bigpicture.md`	Path to bigpicture synthesis output
2	`hub-path`	no	`docs/learnings/cc-bigpicture/`	Directory for learnings hub

Examples:

/persisting-bigpicture-learnings
/persisting-bigpicture-learnings ~/.claude/bigpicture.md
/persisting-bigpicture-learnings bigpicture.md docs/learnings/cc-bigpicture/

Output Structure

docs/learnings/cc-bigpicture/
├── latest.md          # Always the most recent synthesis
└── archive/
    ├── 2026-04-01.md
    ├── 2026-04-03.md
    └── 2026-04-06.md  # Today's snapshot

Workflow

Parse arguments — Apply defaults per Arguments table.
Read input — Read input-path. If the file does not exist, report error and stop.
Create hub directory — Create hub-path and hub-path/archive/ if absent.
Write latest — Write full synthesis content to hub-path/latest.md. Always overwrite — this is the current-state pointer.
Write archive snapshot — Determine today's date (YYYY-MM-DD).
- If hub-path/archive/YYYY-MM-DD.md does not exist, create it with the synthesis content.
- If it does exist, append a --- separator followed by the new synthesis content. This preserves all snapshots from the same day.
Report — Confirm paths written and archive entry count for today.

Integration

Runs after /synthesizing-cc-bigpicture. Chain the two skills:

/synthesizing-cc-bigpicture all 7d bigpicture.md
/persisting-bigpicture-learnings bigpicture.md docs/learnings/cc-bigpicture/

Compound Learning

Other skills can read hub-path/latest.md for prior synthesis context:

synthesizing-cc-bigpicture — Load previous synthesis for incremental update instead of cold start.
ralph / PRD skills — Reference latest bigpicture for strategic context.
compacting-context — Include bigpicture summary when compacting at phase boundaries.

Quality Check

latest.md content matches the most recent archive entry
Archive files are append-only — never overwrite, never delete
Hub path directories created automatically
Input file validated before any writes

---name: persisting-bigpicture-learningsdescription: Persist Bigpicture to Learnings Hub---# Persist Bigpicture to Learnings Hub**Target**: $ARGUMENTSPersists the output of `/synthesizing-cc-bigpicture` as a dated snapshot in alearnings hub. Maintains a `latest.md` pointer (always current) and anappend-only archive for compound cross-session learning.## Arguments| Position | Name | Required | Default | Description ||----------|------|----------|---------|-------------|| 1 | `input-path` | no | `bigpicture.md` | Path to bigpicture synthesis output || 2 | `hub-path` | no | `docs/learnings/cc-bigpicture/` | Directory for learnings hub |**Examples:**```/persisting-bigpicture-learnings/persisting-bigpicture-learnings ~/.claude/bigpicture.md/persisting-bigpicture-learnings bigpicture.md docs/learnings/cc-bigpicture/```## Output Structure```docs/learnings/cc-bigpicture/├── latest.md # Always the most recent synthesis└── archive/ ├── 2026-04-01.md ├── 2026-04-03.md └── 2026-04-06.md # Today's snapshot```## Workflow1. **Parse arguments** — Apply defaults per Arguments table.2. **Read input** — Read `input-path`. If the file does not exist, report error and stop.3. **Create hub directory** — Create `hub-path` and `hub-path/archive/` if absent.4. **Write latest** — Write full synthesis content to `hub-path/latest.md`. Always overwrite — this is the current-state pointer.5. **Write archive snapshot** — Determine today's date (`YYYY-MM-DD`). - If `hub-path/archive/YYYY-MM-DD.md` does **not** exist, create it with the synthesis content. - If it **does** exist, append a `---` separator followed by the new synthesis content. This preserves all snapshots from the same day.6. **Report** — Confirm paths written and archive entry count for today.## IntegrationRuns after `/synthesizing-cc-bigpicture`. Chain the two skills:```/synthesizing-cc-bigpicture all 7d bigpicture.md/persisting-bigpicture-learnings bigpicture.md docs/learnings/cc-bigpicture/```## Compound LearningOther skills can read `hub-path/latest.md` for prior synthesis context:- **synthesizing-cc-bigpicture** — Load previous synthesis for incremental update instead of cold start.- **ralph / PRD skills** — Reference latest bigpicture for strategic context.- **compacting-context** — Include bigpicture summary when compacting at phase boundaries.## Quality Check- `latest.md` content matches the most recent archive entry- Archive files are append-only — never overwrite, never delete- Hub path directories created automatically- Input file validated before any writes

Frequently asked questions

Persisting Bigpicture Learnings