project-calibration-repair
Use when an explicit probabilistic model has a declared inferential or predictive claim and needs calibration-based diagnosis or bounded repair.
Skill by fonnesbeck
Chalk Labs
Need help deploying project-calibration-repair?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/fonnesbeck-project-calibration-repair
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: data
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/project-calibration-repair
What's inside
- Skill name
project-calibration-repair- Description
- Use when an explicit probabilistic model has a declared inferential or predictive claim and needs calibration-based diagnosis or bounded repair. Trigger for statistically misspecified Bayesian/probabilistic models, posterior or prior predictive checks, sampler-health failures, predictive calibration, or a model that runs but may fit data poorly. Do not use for descriptive analysis, reporting-only notebooks, data engineering, deterministic transformations, or projects without an explicit probabilistic model.
- License
- unknown
- Instructions
- 258 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from fonnesbeck/project-skills
- 0.582score
project-retro
fonnesbeck
Use when the user explicitly requests a retrospective on agent workflow and scientific practice.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
project-verifier
fonnesbeck
Use before implementation to design evidence-based acceptance criteria, or afterward to check a bounded data science increment against those predeclared…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
show-me
fonnesbeck
Use to explain data science work visually with compact data-lineage diagrams, model sketches, validation timelines, uncertainty tables, notebook maps, and…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
project-spec
fonnesbeck
Use to clarify a data science goal, interview for consequential decisions, and specify one bounded increment before verifier design and implementation.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
project-implement
fonnesbeck
Use to implement one authorized, bounded data science increment from a current spec, verifier design, and increment-ready environment, then hand real evidence…
SkillAFreshness: A★ 1Claude Code +9 - 0.571score
project-skills-shared
fonnesbeck
Internal shared workflow reference for the project-skills stages.
SkillAFreshness: A★ 1Claude Code +9 - 0.539score
project-environment
fonnesbeck
Use to build a persistent project foundation before any spec, or check its readiness for a current spec and verifier design.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 18, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/fonnesbeck/project-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from fonnesbeck
- 0.582score
project-retro
fonnesbeck
Use when the user explicitly requests a retrospective on agent workflow and scientific practice.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
project-verifier
fonnesbeck
Use before implementation to design evidence-based acceptance criteria, or afterward to check a bounded data science increment against those predeclared…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
show-me
fonnesbeck
Use to explain data science work visually with compact data-lineage diagrams, model sketches, validation timelines, uncertainty tables, notebook maps, and…
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
project-spec
fonnesbeck
Use to clarify a data science goal, interview for consequential decisions, and specify one bounded increment before verifier design and implementation.
SkillAFreshness: A★ 1Claude Code +9 - 0.579score
project-implement
fonnesbeck
Use to implement one authorized, bounded data science increment from a current spec, verifier design, and increment-ready environment, then hand real evidence…
SkillAFreshness: A★ 1Claude Code +9 - 0.571score
project-skills-shared
fonnesbeck
Internal shared workflow reference for the project-skills stages.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get project-calibration-repair running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
project-calibration-repair skill. Agent Mart. https://agentmart.dev/skills/fonnesbeck-project-calibration-repair (last updated 2026-10-24)