Claims
ruvnet/ruflo
Claims-based authorization for agents and operations. An agent skill from ruvnet/ruflo.
Audit graduate-application claims against supplied evidence and return supported, unsupported, stale, or confirmation-required findings.
MITAuto-check passed
Install Evidence Claim Audit
$ npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install Bubble252/offer-harvester evidence-claim-audit --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/Bubble252/offer-harvester.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/evidence-claim-audit .claude/skills/evidence-claim-audit && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "evidence-claim-audit" agent skill from https://github.com/Bubble252/offer-harvester/tree/main/skills/evidence-claim-audit into .claude/skills/evidence-claim-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evidence-claim-audit", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/Bubble252/offer-harvester/tree/main/skills/evidence-claim-auditType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install Bubble252/offer-harvester evidence-claim-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bubble252/offer-harvester.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/evidence-claim-audit .agents/skills/evidence-claim-audit && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "evidence-claim-audit" agent skill from https://github.com/Bubble252/offer-harvester/tree/main/skills/evidence-claim-audit into .agents/skills/evidence-claim-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evidence-claim-audit", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install Bubble252/offer-harvester evidence-claim-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bubble252/offer-harvester.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/evidence-claim-audit .cursor/skills/evidence-claim-audit && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "evidence-claim-audit" agent skill from https://github.com/Bubble252/offer-harvester/tree/main/skills/evidence-claim-audit into .cursor/skills/evidence-claim-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evidence-claim-audit", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/Bubble252/offer-harvester.git --path skills/evidence-claim-audit--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install Bubble252/offer-harvester evidence-claim-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bubble252/offer-harvester.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/evidence-claim-audit .gemini/skills/evidence-claim-audit && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "evidence-claim-audit" agent skill from https://github.com/Bubble252/offer-harvester/tree/main/skills/evidence-claim-audit into .gemini/skills/evidence-claim-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evidence-claim-audit", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install Bubble252/offer-harvester evidence-claim-auditInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/Bubble252/offer-harvester.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/evidence-claim-audit .github/skills/evidence-claim-audit && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "evidence-claim-audit" agent skill from https://github.com/Bubble252/offer-harvester/tree/main/skills/evidence-claim-audit into .github/skills/evidence-claim-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evidence-claim-audit", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install Bubble252/offer-harvester evidence-claim-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/Bubble252/offer-harvester.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/evidence-claim-audit .opencode/skills/evidence-claim-audit && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "evidence-claim-audit" agent skill from https://github.com/Bubble252/offer-harvester/tree/main/skills/evidence-claim-audit into .opencode/skills/evidence-claim-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "evidence-claim-audit", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
evidence-claim-audit- GitHub stars
- 122
- Token cost
- ~427 tokens
- SKILL.md length
- 168 words
- Files
- 5 (incl. scripts, references)
- Skills in repo
- 7
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audit graduate-application claims against supplied evidence and return supported, unsupported, stale, or confirmation-required findings.
- Works in 5 steps: Read references/input-output.md before… → Normalize each claim into text, claim… → Mark a claim supported only when… → …
- Reviewing contact emails
- SKILL.md covers Hard Boundaries and 中文说明
- Runs Python scripts from its folder
What it does
Evidence Claim Audit is an agent skill from Bubble252/offer-harvester. Audit graduate-application claims against supplied evidence and return supported, unsupported, stale, or confirmation-required findings. Use when drafting or reviewing contact emails, statements, recommendation packets, advisor reports, policy summaries, or structured claim lists.
Its SKILL.md is about 430 tokens, which your agent loads only when the skill is triggered. The skill folder holds 7 other files, including scripts and reference files (for example `agents/openai.yaml`, `references/input-output.md` and `scripts/claim_fixture.json`).
The licence is MIT.
When your agent uses it
- Reviewing contact emails
- Recommendation packets
- Advisor reports
- Policy summaries
Example prompts
- “/evidence-claim-audit”
Requirements
- Python 3
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Read references/input-output.md before accepting a new schema or status.
- Normalize each claim into text, claim type, source refs, and a proposed status.
- Mark a claim supported only when supplied evidence directly covers it.
- Mark missing or conflicting support as unsupported, old time-sensitive support as stale, and profile uncertainty as needs_confirmation.
- Preserve source refs and state why a claim is blocked. Do not invent citations.
What it can do on your machine
Read from SKILL.md and the folder at commit c640922. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Ships 2 files in scripts/ (Python), which the agent can run.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Evidence Claim Audit loads about 427 tokens when it runs, and up to ~582 if it reads all its reference files. Until then it costs about 76 tokens; SKILL.md has 168 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.
SKILL.md
The full file from Bubble252/offer-harvester at commit c640922, republished under its MIT licence (© Bubble252). 168 words, ~427 tokens.
Download SKILL.mdSave it as
.claude/skills/evidence-claim-audit/SKILL.md (or your agent's skills folder). This skill also uses 4 other files; get the full folder from GitHub.- name
- evidence-claim-audit
- description
- Audit graduate-application claims against supplied evidence and return supported, unsupported, stale, or confirmation-required findings. Use when drafting or reviewing contact emails, statements, recommendation packets, advisor reports, policy summaries, or structured claim lists.
Evidence Claim Audit
- Read
references/input-output.mdbefore accepting a new schema or status. - Normalize each claim into text, claim type, source refs, and a proposed status.
- Mark a claim
supportedonly when supplied evidence directly covers it. - Mark missing or conflicting support as
unsupported, old time-sensitive support asstale, and profile uncertainty asneeds_confirmation. - Preserve source refs and state why a claim is blocked. Do not invent citations.
Hard Boundaries
- Treat supplied evidence as candidate context, not permission to write profile, tracker, memory, or final material records.
- Never convert an unconfirmed web fact into a confirmed student fact.
- Never hide a rejection, conflict, expiry, or missing source behind a neutral score.
- Return review findings and candidate revisions only. Do not send messages or submit applications.
Run scripts/validate_claim_audit.py --input <claims.json> before publishing a fixture.
中文说明
- 接受新 schema 或状态前，先阅读
references/input-output.md。 - 将每条 claim 规范为文本、类型、来源引用和建议状态。
- 只有提供的证据直接覆盖 claim 时才标为
supported。 - 缺证据或证据冲突标为
unsupported；时效性证据过期标为stale；画像不确定标为needs_confirmation。 - 保留来源引用和阻塞原因，不得编造引文。
强制边界
- 提供的证据只是候选上下文，不能据此写入 profile、tracker、memory 或最终材料。
- 不得把未确认网页事实升级为已确认学生事实。
- 不得用中性分数掩盖 rejected、conflict、expiry 或缺来源。
- 只返回审计结论和候选修改，不发送消息、不提交申请。
© Bubble252, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 4 other files (scripts, references) in skills/evidence-claim-audit of Bubble252/offer-harvester.
- SKILL.md
- agents/openai.yaml
- references/input-output.md
- scripts/claim_fixture.json
- scripts/validate_claim_audit.py
Open the folder on GitHubat commit c640922
Compare with similar skills
Evidence Claim Audit next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Evidence Claim Audit this skillBubble252/offer-harvester | 122 | — | ~427 | Automated safety check: Pass | MIT | |
| Claimsruvnet/ruflo | 74k | 2 repos | ~1.1k | Automated safety check: Pass | MIT | |
| Sbom Supply Chainsickn33/agentic-awesome-skills | 47k | 2 repos | ~3.4k | Automated safety check: Pass | MIT | |
| Agent Supply Chaingithub/awesome-copilot | 40k | 1 repos | ~2.7k | Automated safety check: Pass | MIT | |
| Supply Chain Securityzhaoxuya520/reverse-skill | 41k | 4 repos | ~953 | Automated safety check: Warn | MIT | |
| Returns Reverse Logisticssickn33/agentic-awesome-skills | 47k | 8 repos | ~6.4k | Automated safety check: Pass | MIT |
Similar skills
Sbom Supply Chain
sickn33/agentic-awesome-skills
Generate, sign, and verify SBOMs and provenance attestations to secure the software supply chain.
- Official
Agent Supply Chain
github/awesome-copilot
Verify supply chain integrity for AI agent plugins, tools, and dependencies.
Supply Chain Security
zhaoxuya520/reverse-skill
A skill your agent uses for software supply-chain security assessment covering SBOM, SCA, CI/CD pipelines, container images, build integrity, dependency provenance, and vulnerability reachability.
Returns Reverse Logistics
sickn33/agentic-awesome-skills
Codified expertise for returns authorisation, receipt and inspection, disposition decisions, refund processing, fraud detection, and warranty claims management.
Implementing Supply Chain Security With In Toto
mukul975/Anthropic-Cybersecurity-Skills
Implements supply chain integrity verification for container builds with the in-toto framework: generating signing keys, defining a supply chain layout, recording pipeline steps as signed link…
More from Bubble252/offer-harvester
Grad Apply Workflow
Bubble252/offer-harvester
Evidence-grounded graduate application workflow protocols for this repository.
Profile Field Normalization
Bubble252/offer-harvester
Normalize graduate-application profile fields while preserving field evidence, source provenance, confidence, and confirmation status.
Source Connector Authoring
Bubble252/offer-harvester
Design and validate safe source connector manifests for public graduate-admission, policy, advisor, lab, and community sources.
Advisor Due Diligence
Bubble252/offer-harvester
Build an evidence-grounded advisor review covering identity, research direction, recruitment signals, lab context, source gaps, and community risk signals.
Contact Email Coach
Bubble252/offer-harvester
Prepare evidence-grounded graduate-advisor contact email candidates with review and audit findings.
Recommendation Letter Helper
Bubble252/offer-harvester
Prepare evidence-grounded recommendation requests, recommender material packets, and clearly labeled reference drafts for graduate applications.
Questions about Evidence Claim Audit
What does Evidence Claim Audit do?
Audit graduate-application claims against supplied evidence and return supported, unsupported, stale, or confirmation-required findings. Evidence Claim Audit is an agent skill from Bubble252/offer-harvester. Audit graduate-application claims against supplied evidence and return supported, unsupported, stale, or confirmation-required findings.
When should I use Evidence Claim Audit?
Evidence Claim Audit fits situations like: reviewing contact emails; recommendation packets; advisor reports; policy summaries.
How do I install Evidence Claim Audit in Claude Code?
Run `npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a claude-code`. Or copy the skill folder (skills/evidence-claim-audit in Bubble252/offer-harvester) into .claude/skills/evidence-claim-audit in your project. Claude Code loads it when a task matches its description.
How do I install Evidence Claim Audit in Codex?
Run `npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a codex`. Or copy the skill folder (skills/evidence-claim-audit in Bubble252/offer-harvester) into .agents/skills/evidence-claim-audit in your project. Codex loads it when a task matches its description.
Can I use Evidence Claim Audit in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add Bubble252/offer-harvester --skill evidence-claim-audit -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/evidence-claim-audit, .gemini/skills/evidence-claim-audit, .github/skills/evidence-claim-audit and .opencode/skills/evidence-claim-audit in your project.
What does Evidence Claim Audit need to run?
Going by SKILL.md and its folder, Evidence Claim Audit needs Python for the scripts in its folder. Our summary lists: Python 3.
Does Evidence Claim Audit access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Evidence Claim Audit safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.
What licence does Evidence Claim Audit use?
Evidence Claim Audit is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Evidence Claim Audit use?
About 427 tokens (SKILL.md is roughly 1.7k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full. Its references folder adds about 155 tokens, read only when the agent opens those files.
What are the alternatives to Evidence Claim Audit?
Skills that share tags, products or a category with Evidence Claim Audit: Claims (ruvnet/ruflo, 74k stars), Sbom Supply Chain (sickn33/agentic-awesome-skills, 47k stars), Agent Supply Chain (github/awesome-copilot, 40k stars) and Supply Chain Security (zhaoxuya520/reverse-skill, 41k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Evidence Claim Audit?
Bubble252 (a GitHub user) maintains it in Bubble252/offer-harvester, which has 122 GitHub stars. The repository holds 7 skills in this directory. The repository was last updated on August 27, 2026.
Source: Bubble252/offer-harvester on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.