ai-disclosure
Skill26k starsChanged 9 months agoMITView on GitHub
Track and document Claude's contributions during coding sessions for PR transparency. Use when working on feature branches, PRs, or when the user wants to maintain AI contribution records. Maintains a disclosure file per branch summarizing Claude's involvement.
3 other projects use a version of this.
Adopted by
Steady: 0 new projects took it in the last 4 weeks, none the 4 weeks before.thin data
Most recently taken up by
- nguyenbui1105/first-1000-playerstheir own version, first seen Nov 15, 2026
- pradyumnasagar/open-research-skillstheir own version, first seen Nov 8, 2026
- Ricardo-kui/claude-skillstheir own version, first seen Sep 10, 2026
Who's talking about shap/shap
- Vizuara“Lecture 9 - Understanding SHAP | Explainable AI (XAI) | Shapley values | Interpreting black box ML”YouTube · Jun 10, 2024 · 14k views
- Vizuara“Lecture 11 - SHAP for image-based data | Explainable AI (XAI) | Image plot | Colab Implementation”YouTube · Jun 15, 2024 · 5.1k views
- Vizuara“Lecture 12 - SHAP for tabular data | Explainable AI (XAI) | Image plot | Colab Implementation”YouTube · Jun 17, 2024 · 4.6k views
- Vizuara“Lecture 10 - SHAP for text-based data | Explainable AI (XAI) | Force plot | Colab Implementation”YouTube · Jun 12, 2024 · 3.2k views
- Metachiki / 2021“貢献度の計算方法|Shapley値と機械学習への応用(SHAP)”YouTube · Aug 23, 2025 · 1.7k views
The biggest 5 of 65 mentions linking to the repository that our crawl found. Each line is their own headline.
See all 65
Talked about on GitHub, YouTube, Hacker News and Stack Overflow (65 times).
On GitHub · 50
- Apr 9, 2025Identification of "load bearing walls" that need attention — scientific-python/summit-20257 reactions · 3 comments
- Mar 3, 2024Duplicate OpenMP causes deadlocks/crashes — pytorch/pytorch7 reactions · 19 comments
- Aug 17, 2026build(deps): bump the python-runtime group across 1 directory with 17 updates — muratmiracg-dev/Manufacturing-Quality-OEE-Predictive-Maintenance-Control-Tower2 reactions · 4 comments
- Oct 12, 2023Support for shap==0.43.0 — ing-bank/probatus2 reactions · 6 comments
- Jun 24, 2026[skill-health] shap: fix stale GitHub repo link — stanfish06/skillquarium1 reaction · 1 comment
45 more on GitHub
- Apr 15, 2026About to drop Cython for nanobind + scikit-build-core — conda-forge/shap-feedstock1 reaction
- Mar 23, 2025#820: Update Jupyter Notebook with causal trees interpretation examples — uber/causalml1 reaction
- Nov 21, 2024`uv pip compile` Ignores Lower Bound for Transitive Dependency — astral-sh/uv1 reaction · 7 comments
- Aug 7, 2024[python-package] SegFault on MacOS when pytorch is installed — lightgbm-org/LightGBM1 reaction · 11 comments
- Aug 1, 2024feature_perturbationのtypo? — ayukat1016/lightgbm_sample1 reaction · 3 comments
- Feb 14, 2024[ci] no-response bot is broken — lightgbm-org/LightGBM1 reaction · 8 comments
- Nov 10, 2026Update shap requirement from >=0.45.0 to >=0.54.1 in /backend — rubliproject/rubli0 reactions
- Nov 8, 2026chore(deps): bump shap from 0.52.0 to 0.54.1 — MohammedAlkindi/proofx0 reactions · 2 comments
- Nov 2, 2026build(deps): update shap requirement from >=0.45 to >=0.49.1 — smshagor-dev/CyberPhotonics-SPR0 reactions
- Nov 2, 2026chore(deps): bump shap from 0.50.0 to 0.54.1 in /requirements/in — FullStackWithLawrence/ai-algorithms0 reactions · 1 comment
- Nov 1, 2026build(deps): bump the ml group across 1 directory with 3 updates — Vanshcloud/Transfer-Value-Predictor0 reactions · 1 comment
- Oct 30, 2026chore(deps-dev): update shap requirement from >=0.45.0 to >=0.51.0 in /backend — haomingkoo/lionweather0 reactions
- Oct 28, 2026chore(deps): bump shap from 0.53.0 to 0.54.1 — hansdarmawann/ibmhratt0 reactions
- Oct 27, 2026build(deps): bump shap from 0.50.0 to 0.54.1 in /api — tulasiram2005/servicestock-ai0 reactions
- Oct 26, 2026build(deps-dev): update shap requirement from <0.47,>=0.45 to >=0.45,<0.52 in /backend — anubhab7105/Ouroboros0 reactions
- Oct 25, 2026Bump shap from 0.53.0 to 0.54.1 — elias-orellana-91/02-ml-volatilidad0 reactions
- Oct 25, 2026chore(deps): bump shap from 0.52.0 to 0.54.1 — surybang/python_data0 reactions
- Oct 25, 2026Bump shap from 0.47.2 to 0.54.1 — MallamTeja/f1_models0 reactions · 1 comment
- Oct 23, 2026Update shap requirement from >=0.44 to >=0.49.1 — shivasathvik44/URL-PD0 reactions · 1 comment
- Oct 23, 2026chore(deps): bump shap from 0.52.0 to 0.54.1 in /services/ml — Santidelacarrera/NexusFlow-AI0 reactions
- Oct 23, 2026chore(deps): update shap requirement from >=0.46 to >=0.54.1 in /training — Culzz/trustscore0 reactions · 1 comment
- Oct 21, 2026[Wheel monitor] shap - Windows Arm64 — CoreCollective-dev/windows-on-arm-wg0 reactions · 1 comment
- Oct 21, 2026chore(deps): update shap requirement from >=0.53.0 to >=0.54.1 in /backend — AkshatRaj00/Heart-diseaseprediction0 reactions · 3 comments
- Oct 20, 2026build(deps-dev): bump shap from 0.52.0 to 0.54.1 — LL-11/commodity_forecasting0 reactions
- Oct 20, 2026chore(deps): update shap requirement from <0.53,>=0.52 to >=0.52,<0.55 — Parmodk2310/CreditScorev4-ML-Governance0 reactions · 1 comment
- Oct 19, 2026Update shap requirement from >=0.52.0 to >=0.54.1 — LoganMazurek/Kona-AI-ML0 reactions
- Oct 16, 2026Update shap to 0.54.1 — naturalis/sdmdl0 reactions
- Oct 12, 2026Bump shap from 0.49.1 to 0.51.0 — WithPrecedent/amos0 reactions · 1 comment
- Oct 8, 2026[deps](deps): Update shap requirement from >=0.42.0 to >=0.52.0 — shreyas026/SuggestAlgo-AI0 reactions · 1 comment
- Oct 2, 2026Update shap requirement from >=0.45.0 to >=0.52.0 in /geo-ml — Harshitver0511/tvs0 reactions · 1 comment
- Oct 1, 2026Update shap requirement from >=0.45.0 to >=0.52.0 — edward-dev23/Quantitative-Analysis-Project0 reactions · 1 comment
- Sep 28, 2026chore(deps)(deps): bump shap from 0.46.0 to 0.51.0 — mohmdstag7-cmd/Tr0 reactions
- Sep 27, 2026build(deps): bump shap from 0.51.0 to 0.52.0 in /services/ai-api — Horus031/lumivox0 reactions · 2 comments
- Sep 27, 2026deps: bump shap from 0.46.0 to 0.52.0 — DiogoRibeiro7/mlops-python-package0 reactions
- Sep 26, 2026Update shap requirement from >=0.46 to >=0.49.1 — rnanda19/Customer360_Navigator_Enterprise_Suite0 reactions · 1 comment
- Sep 12, 2026Update shap requirement from >=0.44.0 to >=0.52.0 — nithin8407/customer-churn-prediction-system0 reactions
- Aug 29, 2026build: update shap requirement from >=0.44.0 to >=0.52.0 — mohammedjashir1436/VoiceGuard0 reactions
- Aug 10, 2026chore(deps): Bump shap from 0.45.1 to 0.49.1 — tjjerome/Sportstradamus0 reactions
- Aug 5, 2026Update shap requirement from >=0.44.0 to >=0.49.1 — Bhaskar19chowdary/bsscl-gbm0 reactions
- Mar 31, 2026ENH: SHAP explainer does not accept local fig, ax handles — lanl/ldrd_neat_ml0 reactions · 10 comments
- Nov 9, 2025Image Imputer — Advueu963/imputer0 reactions
- Nov 5, 2025[⭐] Can the SHAP function be added? — GestaltCogTeam/BasicTS0 reactions
- Jul 25, 2025shap instability: additivity check fails — basf/MolPipeline0 reactions
- May 14, 2025[long term] feature importance for models with SHAP — OpenADMET/openadmet-models0 reactions · 2 comments
- May 15, 2024BUG: SHAP values calculated using CPU differ from SHAP values calculated using GPU for XGBOOST — dmlc/xgboost0 reactions · 1 comment
On YouTube · 13
- Jun 10, 2024Lecture 9 - Understanding SHAP | Explainable AI (XAI) | Shapley values | Interpreting black box ML — Vizuara14k views · 11 comments
- Jun 15, 2024Lecture 11 - SHAP for image-based data | Explainable AI (XAI) | Image plot | Colab Implementation — Vizuara5.1k views · 6 comments
- Jun 17, 2024Lecture 12 - SHAP for tabular data | Explainable AI (XAI) | Image plot | Colab Implementation — Vizuara4.6k views · 4 comments
- Jun 12, 2024Lecture 10 - SHAP for text-based data | Explainable AI (XAI) | Force plot | Colab Implementation — Vizuara3.2k views · 2 comments
- Aug 23, 2025貢献度の計算方法|Shapley値と機械学習への応用(SHAP) — Metachiki / 20211.7k views · 6 comments
8 more on YouTube
- Nov 15, 2024Predict the Contribution of Each Channel to Revenue? Use this Free App! — Marketing Analytics With Kisholoy154 views · 2 comments
- Aug 7, 20254 Tools Every AI Ethicist Must Know #aiethics #responsibleai #automatedsolutions #aiethicist — TechHotTea125 views · 2 comments
- Sep 20, 2025Unlock AI's Black Box: The Ultimate Guide to SHAP for Explainable AI (2025) — Retured117 views
- Jan 12, 2025Can You Afford to Ignore AI ETHICS as a Developer? — The Scripting Den86 views · 2 comments
- Dec 4, 2023Validating Machine Learning Systems For Safety Critical Applications With Ketryx — Tobias Macey61 views
- May 20, 2025SHAP 오픈소스를 통해 이해하는 XAI 핵심 개념 — 한신대학교SW중심대학사업단33 views
- Jul 1, 2025S1:EP4 Can You Trust AI? Unpacking Explainable AI (XAI) & Building Trust — She Explores the Cosmos31 views
- Jul 6, 2024Validating Machine Learning Systems For Safety Critical Applications With Ketryx — Tobias Macey27 views
On Hacker News · 1
- Mar 8, 2024Shap v0.45.01 point · 1 comment
On Stack Overflow · 1
- Jan 26, 2025SHAP DeepExplainer Error: 'tuple' object has no attribute 'as_list' 'device'0 votes
Other versions3 projects use a version of this.
Word for word · 0
None found.
Edited · 0
None found.
Wrote their own version · 3
- pradyumnasagar/open-research-skills★ 8same name
- nguyenbui1105/first-1000-players★ 1same name
- Ricardo-kui/claude-skills★ 0same name
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.
The file
Show its rules and text
We split this skill into the rules it gives an agent
13 rules. About 0 are common, 13 are distinctive, and 0 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈13
Distinctive · estimate
This author's own choices. Worth a look.
0
Very specific
Tied to their project's names, files or tools. Probably skip.
- Common
- Distinctive
- Very specific
- Distinctive: line 26
When starting work on a feature branch, offer once:
- Distinctive: line 30
If yes, create the disclosure file and begin tracking.
- Distinctive: line 34
Only track contributions made AFTER the user opts in: Do not backfill anything from earlier in the conversation, even if it seems relevant …
- Distinctive: line 36
After significant actions (writing functions, fixing bugs, refactoring):
- Distinctive: line 44
Only use the disclosure file to track contributions — do not rely on in-context memory of what happened before opt-in.
- Distinctive: line 46
No prompts during work—just silently maintain the record.
- Distinctive: line 50
When user requests summary or creates a PR:
- Distinctive: line 55
Use git diff or read the files to see if user modified them after you
- Distinctive: line 59
If user significantly modified your code afterward → downgrade to Assisted
- Distinctive: line 60
If user corrected your approach multiple times → downgrade to Assisted
- Distinctive: line 61
Add note: "co-creation with significant user involvement"
- Distinctive: line 103
Downgrade rule: If user significantly modified your code or corrected your approach repeatedly, downgrade from Autonomous to Assisted and …
- Distinctive: line 127
When user creates a PR, offer a copy-paste block:
≈ “Common” is an estimate: at least 1 in 5 of the 364,980 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
AI Disclosure Tracking
Track Claude's contributions during coding sessions and maintain a disclosure file for PR transparency.
Involvement Levels
- Autonomous - Claude wrote the code/solution independently
- Assisted - Claude implemented based on user direction
- Advised - Claude provided guidance that user implemented
File Location
Disclosure file: .claude/disclosures/<branch-name>.md
Get branch name with git branch --show-current. If not in a git repo, use session-<date>.
Workflow
1. Opt-in
When starting work on a feature branch, offer once:
"Would you like me to track AI contributions for this branch?"
If yes, create the disclosure file and begin tracking.
2. Track Silently
Only track contributions made AFTER the user opts in. Do not backfill anything from earlier in the conversation, even if it seems relevant to the branch. The disclosure file starts as a clean slate from the moment the user says yes.
After significant actions (writing functions, fixing bugs, refactoring):
- Log the contribution - Append to the appropriate section in the disclosure file
- Record what you changed - Track in the internal section:
- Which files you touched
- Brief summary of what you wrote/changed
- Initial involvement level
Only use the disclosure file to track contributions — do not rely on in-context memory of what happened before opt-in.
No prompts during work—just silently maintain the record.
3. Verify and Generate Summary
When user requests summary or creates a PR:
- Check your work against current state:
- Review files you logged as touching
- Compare current file contents against what you originally wrote
- Use
git diffor read the files to see if user modified them after you - Also recall from conversation context: did user correct you? Ask for changes? Rewrite parts?
- Downgrade if needed:
- If user significantly modified your code afterward → downgrade to Assisted
- If user corrected your approach multiple times → downgrade to Assisted
- Add note: "co-creation with significant user involvement"
- Generate the summary with accurate involvement levels
Disclosure File Format
# AI Disclosure for branch: <branch-name>
## Summary
[Generated on request]
## Contributions
### Autonomous
- [One-line descriptions of independent work]
### Assisted
- [One-line descriptions of directed work]
### Advised
- [One-line descriptions of guidance provided]Internal Tracking
Track your changes in an HTML comment (not shown in final summary):
<!--
CHANGES:
- src/partition.py: wrote repartitioning logic (autonomous)
- tests/test_partition.py: wrote validation tests (autonomous)
- src/boundaries.py: implemented boundary calc (autonomous)
CORRECTIONS:
- src/boundaries.py: user fixed off-by-one error (count: 2)
-->This record lets you verify at summary time whether files still contain what you wrote, or if the user significantly changed them.
Downgrade rule: If user significantly modified your code or corrected your approach repeatedly, downgrade from Autonomous to Assisted and note: "co-creation with significant user involvement".
Example Output
# AI Disclosure for branch: feature/healpix-partitioning
## Summary
Claude assisted with repartitioning logic (co-creation with significant human involvement), autonomously wrote test cases, and advised on spatial indexing approaches.
## Contributions
### Autonomous
- Wrote test cases for HEALPix partition validation
### Assisted
- Implemented repartitioning logic based on user requirements
### Advised
- Suggested using spatial indexing for performancePR Format
When user creates a PR, offer a copy-paste block:
## AI Disclosure
Developed with Claude assistance:
- **Autonomous**: [list]
- **Assisted**: [list]
- **Advised**: [list]
Details: `.claude/disclosures/<branch>.md`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.

