dual-source-honesty
Keep fetch-time catalogs distinct from corrected bibliographies; keep measured, derived, and estimated values distinct.
Skill by ricfulop
Chalk Labs
Need help deploying dual-source-honesty?
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/ricfulop-dual-source-honesty
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
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/dual-source-honesty
What's inside
- Skill name
dual-source-honesty- Description
- Keep fetch-time catalogs distinct from corrected bibliographies; keep measured, derived, and estimated values distinct. Use when cataloging papers or quoting a number's status.
- License
- MIT
- Instructions
- 37 lines in SKILL.md · view on GitHub
Files (1)
- SKILL.md
SKILL.md (first lines)
# Dual-source honesty Two records can disagree. A disagreement is a decision request, not permission to copy one side over the other. ## Literature - The fetch-time catalog (`catalog.json` or equivalent) is what the search returned. Leave it as-is. - Bibliography field corrections go in `refs.bib` (or the project's bibliography) plus a register. - Empty author lists stay empty rather than invented. Truncated three-author records that were not confirmed stay `and others`. - A catalog count is not a reading count. ## Numbers Workbook or table status words are load-bearing and are not synonyms: | status | meaning | |---|---| | MEASURED | an instrument or a run produced it | | DERIVED | computed from named inputs that exist | | CATALOG | a vendor or index field | | ESTIMATE | judgment, bounded if possible | | blank / NR / TBD / PLACEHOLDER | unknown — do not fill from adjacent cells | Do not infer procurement metadata from a model-spec column, or a canon value from manuscript prose. When two owners hold disjoint fields, record the decision rather than silently merging. ## What this is not Private correspondence pasted into chat is background, not quotable material, unless the author clears the specific quote.
From ricfulop/cba-agentic-engineering-bootstrap, MIT.
More from ricfulop/cba-agentic-engineering-bootstrap
- 0.552score
paper-lookup
ricfulop
Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
domain-corpus-bootstrap
ricfulop
Become a domain expert in X by building a reproducible, legally-acquired literature corpus for a new project or topic — topic map, checked-in query manifest…
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
prereg-freeze
ricfulop
Hash-bound preregistration before confirmatory runs.
SkillBFreshness: B★ 1Claude Code +9 - 0.546score
figure-style
ricfulop
Pointer to APS, Nature, and Science figure skills plus lib/styles.py.
SkillBFreshness: B★ 1Claude Code +9 - 0.545score
mit-presentation
ricfulop
Build academic PowerPoint decks from the official MIT Arial template.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
literature-corpus
ricfulop
Pointer to domain-corpus-bootstrap.
SkillBFreshness: B★ 1Claude Code +9 - 0.540score
pymc
ricfulop
Bayesian modeling with PyMC.
SkillBFreshness: B★ 1Claude Code +9 - 0.294score
aps-figure-style
ricfulop
No description from the publisher yet.
SkillBFreshness: B★ 1Claude Code +9 - 0.294score
manuscript-prose-style
ricfulop
No description from the publisher yet.
SkillBFreshness: B★ 1Claude Code +9 - 0.294score
nature-figure-style
ricfulop
No description from the publisher yet.
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 2, 2026 (2 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from ricfulop
- 0.552score
paper-lookup
ricfulop
Search 10 academic paper databases via REST APIs for research papers, preprints, and scholarly articles.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
prereg-freeze
ricfulop
Hash-bound preregistration before confirmatory runs.
SkillBFreshness: B★ 1Claude Code +9 - 0.547score
domain-corpus-bootstrap
ricfulop
Become a domain expert in X by building a reproducible, legally-acquired literature corpus for a new project or topic — topic map, checked-in query manifest…
SkillBFreshness: B★ 1Claude Code +9 - 0.546score
figure-style
ricfulop
Pointer to APS, Nature, and Science figure skills plus lib/styles.py.
SkillBFreshness: B★ 1Claude Code +9 - 0.545score
mit-presentation
ricfulop
Build academic PowerPoint decks from the official MIT Arial template.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
literature-corpus
ricfulop
Pointer to domain-corpus-bootstrap.
SkillBFreshness: B★ 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 dual-source-honesty 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
dual-source-honesty skill. Agent Mart. https://agentmart.dev/skills/ricfulop-dual-source-honesty (last updated 2026-10-24)