cv-promote-guard
Skill2 starsChanged 42 days agoMITView on GitHub
Strict self-guarded mechanism for reading an external CV source (e.g. cvdata.json in a portfolio repo) for grounding and safely promoting insights back with sidecars, diffs, previews, backups, and explicit user confirmation. Never mutates external profile without multiple gates. Use for CV-related logic in finder-reactor or prep flows. Sidecar-first, auditable, intervention points. Fission for safe edit code; fusion for protecting the public profile while improving future matches.
In this repository49 other files it gives its agents.
- AGENTS.mdAGENTS.md
- adversarial-auditSkill
- agentic-reactorSkill
- agent-orchestratorSkill
- ai-optimizationSkill
- architecture-synthesisSkill
- audit-allow-buildsSkill
- audit-ide-dependenciesSkill
- author-workflow-skillSkill
- bdd-strategizerSkill
- chrome-extension-mv3Skill
- concurrent-cli-agentsSkill
- control-feederSkill
- control-graphSkill
- cursor-transcript-harvestSkill
- devcontainer-hardenedSkill
- dual-copy-skill-publishSkill
- explore-repo-readonlySkill
- finder-reactorSkill
- fix-dependency-securitySkill
- fusion-sageSkill
- git-worktreesSkill
- grok-host-prepSkill
- gt-flowSkill
- higher-order-decision-architectSkill
- looperSkill
- master-plannerSkill
- mvu-refactor-planSkill
- odysseus-navigatorSkill
- project-editor-profileSkill
- react-client-expertSkill
- semantic-markup-cssSkill
- semantic-nameSkill
- session-unit-orderSkill
- shell-kernel-ontologySkill
- skill-rename-propagationSkill
- split-to-prsSkill
- src-tree-reorganizeSkill
- stellar-roadmapSkill
- stellar-spacemapSkill
- subagent-delegationSkill
- subagent-explore-reportSkill
- supply-chain-hardenSkill
- tauri-agenticSkill
- tauri-ipc-debugSkill
- tidy-commit-pushSkill
- upgrade-packagesSkill
- verification-cockpitSkill
- x-agent-resourcesSkill
The file
We split this skill into the rules it gives an agent
4 rules. About 0 are common, 3 are distinctive, and 1 is very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈3
Distinctive · estimate
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
- Very specific: line 12
Sidecar-First Always: All proposed changes go to a sidecar (e.g.
- Distinctive: line 30
Never send full multi-hundred-line JSON to LLM by default.
- Distinctive: line 39
No direct mutation of external CV without this guard module.
- Distinctive: line 40
Always produce sidecar proposal even for internal suggestions.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Files
CV Promote Guard — Safe, Auditable, Sidecar-First Profile Evolution
Core Mission: Allow opportunity finders to use the user's real CV for hyper-relevant analysis and prep, while making any "promote insights" (suggested improvements to headline, experience bullets, skills, etc.) completely safe, reversible, and user-controlled.
Immutable Principles
- Sidecar-First Always: All proposed changes go to a sidecar (e.g.
preps/<id>/cv-delta.json) before any master edit. - External Repo is Sacred: The configured profile checkout is read-only by default. Writes require multi-step confirmation + diff preview.
- Multiple Guards & Pauses: prune on read; diff preview +
.bakon promote; extra pause for public-facing fields. - Full Audit & Reversible: Log source opportunity, rationale, deltas, user decision. Git-friendly patch output.
- Composability: Exposed as guarded MCP tool — agents suggest, never force promotes.
Reactor Integration
In finder-reactor loop:
- Analyze/Prep: load pruned CV packet from configured
cv_repo_path(e.g.src/data/cvdata.json). - Promote flow: generate delta → sidecar → preview → confirm → safe write + backup.
- Guard triggers: "Is this promoting to live public CV? Pause."
Implementation Patterns
Loading & Pruning (Fission):
- Config:
cv_repo_path(user picks once, stored securely). - Prune: relevant sections only (recent roles matching keywords, top projects, skills, headline, contact).
- Never send full multi-hundred-line JSON to LLM by default.
Preview & Apply:
- Desktop UI: diff viewer with checkboxes per edit.
- MCP:
promote_with_preview(insights)→ diff + requires confirm. - On apply: backup (
cvdata.json.bak-<ts>), apply edits (json-patch or manual), return rebuild instructions for the portfolio repo.
Guardrails
- No direct mutation of external CV without this guard module.
- Always produce sidecar proposal even for internal suggestions.
- User can configure "never auto-write", "always require 2 confirms", "dry-run only".
- On error: rollback from
.bak.
Related Skills
finder-reactor, x-agent-resources, tauri-agentic, ai-optimization, fusion-sage.
Example provenance: collab-finder + devprofile CV repo pattern.
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.