harvest
Skill4 starsChanged 11 days agoMITView on GitHub
End-of-session content harvest. Trigger on harvest this session, pull content seeds, any content in this. Writes 1-3 receipt-backed X-voice seeds to outputs and never posts.
We split this skill into the rules it gives an agent
2 rules. 0 are common, 1 is distinctive, and 1 is very specific to this project.
0
Common
Most of the 10 edited versions we read keep these.
1
Distinctive
This author's own choices. Worth a look.
1
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 13
Read CLAUDE.md before executing.
- Very specific: line 19
Do not edit this file directly.
“Common” is measured: kept by at least 6 in 10 of the 10 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
<!-- GENERATED by scripts/sync-agent-adapters from ai/AGENT_ROUTES.json. DO NOT EDIT. -->harvest skill adapter
Canonical skill: skills/harvest/SKILL.md. Read that file in full before acting, then follow it exactly.
This adapter exists so a runtime that discovers repository skills under .agents/skills/ or .claude/skills/ can reach a skill whose canonical copy lives in skills/. It owns no procedure. Do not restate, shorten, or improvise the canonical steps, and do not treat this summary as the skill.
Read CLAUDE.md before executing. It is the shared operating contract and it outranks this skill on precedence, voice, pricing policy, and what counts as a sanctioned write. The canonical skill wins on execution mechanics.
First-party skill of this operating system. Its verification gates are mandatory, never skippable for work that looks quick, and a clean gate is not send authority: nothing client-facing leaves without the operator's explicit go on that specific artifact.
Maintenance
Do not edit this file directly. Change skills/harvest/SKILL.md for procedure or ai/AGENT_ROUTES.json for routing, then run scripts/sync-agent-adapters --write. scripts/repo-doctor blocks stale generated surfaces.
Other versions13 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 13
- huytieu/COG-second-brain★ 1.3ksame name
- egregore-labs/egregore★ 293same name
- darkroomengineering/cc-settings★ 52same name
- toustifer/dsh-harvest★ 10same name
- sergeeey/Claude-cod-top-2026★ 9same name
- FabianoArthur/claude-code-kitchen★ 4same name
- BI-Blitzer/tandem-tokens★ 1same name
- cwade12c/spicerack★ 1same name
- holylight1979/AtomicMemory-ClaudeCode★ 1same name
- yiyaw-lab/agent-armor★ 1same name
3 more not listed
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.
Used alongsideProjects with it also use handoff.
Other files people use alongside this one.
Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
MicrosoftSkillhandoff
Compact the current conversation into a handoff document for another agent to pick up.
Also in 3 projects that use this
In this repository92 other files it gives its agents.
- AGENTS.mdAGENTS.md
- CLAUDE.mdCLAUDE.md
- .github/copilot-instructions.mdCopilot instructions
- analytics-trackingSkill
- app-store-screenshotsSkill
- business-profile-creatorSkill
- call-debriefSkill
- copy-editingSkill
- copywritingSkill
- daily-logSkill
- decision-gauntletSkill
- deep-researchSkill
- hard-taskSkill
- harvestSkill
- invoice-creatorSkill
- landing-pageSkill
- make-interfaces-feel-betterSkill
- ogilvySkill
- onboardSkill
- operational-enterprise-aiSkill
- page-croSkill
- pricing-pageSkill
- product-proof-saasSkill
- proposal-creatorSkill
- prospect-briefSkill
- research-doctrineSkill
- run-coding-sessionSkill
- schema-markupSkill
- seo-auditSkill
- stop-slopSkill
- tailwind-v4Skill
- visual-style-presetsSkill
- web-design-guidelinesSkill
- analytics-trackingSkill
- app-store-screenshotsSkill
- business-profile-creatorSkill
- call-debriefSkill
- copy-editingSkill
- copywritingSkill
- daily-logSkill
- decision-gauntletSkill
- deep-researchSkill
- hard-taskSkill
- invoice-creatorSkill
- landing-pageSkill
- make-interfaces-feel-betterSkill
- ogilvySkill
- onboardSkill
- operational-enterprise-aiSkill
- page-croSkill
- pricing-pageSkill
- product-proof-saasSkill
- proposal-creatorSkill
- prospect-briefSkill
- research-doctrineSkill
- run-coding-sessionSkill
- schema-markupSkill
- seo-auditSkill
- stop-slopSkill
- tailwind-v4Skill
- The first 60 shown.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
Reviews can't be read right now.
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.

