Agent skill

Climate Projection

by lzwei196 in lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation

Climate change impact assessment using CMIP6 data. An agent skill from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.

MITAuto-check passed

Install Climate Projection

skills CLI

$ npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation climate-projection --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.git skills-src && mkdir -p .claude/skills && cp -r skills-src/models/Climate_Projection .claude/skills/climate-projection && rm -rf skills-src

Use ~/.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/

Paste into Claude Code

Install the "climate-projection" agent skill from https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation/tree/main/models/Climate_Projection into .claude/skills/climate-projection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "climate-projection", 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

$skill-installer install https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation/tree/main/models/Climate_Projection

Type 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.

skills CLI

$ npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation climate-projection --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.git skills-src && mkdir -p .agents/skills && cp -r skills-src/models/Climate_Projection .agents/skills/climate-projection && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "climate-projection" agent skill from https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation/tree/main/models/Climate_Projection into .agents/skills/climate-projection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "climate-projection", 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.

skills CLI

$ npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation climate-projection --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/models/Climate_Projection .cursor/skills/climate-projection && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "climate-projection" agent skill from https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation/tree/main/models/Climate_Projection into .cursor/skills/climate-projection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "climate-projection", 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

$ gemini skills install https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.git --path models/Climate_Projection

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation climate-projection --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/models/Climate_Projection .gemini/skills/climate-projection && rm -rf skills-src

Use ~/.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/

Paste into Gemini CLI

Install the "climate-projection" agent skill from https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation/tree/main/models/Climate_Projection into .gemini/skills/climate-projection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "climate-projection", 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.

GitHub CLI

$ gh skill install lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation climate-projection

Installs 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).

skills CLI

$ npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.git skills-src && mkdir -p .github/skills && cp -r skills-src/models/Climate_Projection .github/skills/climate-projection && rm -rf skills-src

Use ~/.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/

Paste into GitHub Copilot

Install the "climate-projection" agent skill from https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation/tree/main/models/Climate_Projection into .github/skills/climate-projection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "climate-projection", 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.

skills CLI

$ npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation climate-projection --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/models/Climate_Projection .opencode/skills/climate-projection && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "climate-projection" agent skill from https://github.com/lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation/tree/main/models/Climate_Projection into .opencode/skills/climate-projection/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "climate-projection", 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: climate-projection
GitHub stars: 201
Token cost: ~3.9k tokens
SKILL.md length: 1,234 words
Files: 22
Skills in repo: 2
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: MIT

At a glance

Climate change impact assessment using CMIP6 data. An agent skill from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.

Works in 4 steps: Stationarity of sub-daily patterns: The… → Limited to China: The bias-corrected… → Baseline period matters: The CMFD/MSWX… → …
SKILL.md covers KI map — what to read, and when, Data Preparation, When to Use This Skill and Pipeline Overview, plus 7 more sections
Runs Python scripts from its folder; calls python and python3

What it does

Climate Projection is an agent skill from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation. Climate change impact assessment using CMIP6 data. Two extraction paths — China (26 models, local files) or Global (34 models, NASA NEX-GDDP-CMIP6 API). Computes delta-change signals, generates future VIC forcing, runs multi-model ensemble analysis.

Its SKILL.md is about 3.9k tokens, which your agent loads only when the skill is triggered. The skill folder holds 25 other files (for example `dag.yaml`, `diagnostics/error_log.yaml` and `diagnostics/format_transformations.yaml`).

It works with Python. The licence is MIT.

Example prompts

“/climate-projection”

Requirements

Python 3

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

Stationarity of sub-daily patterns: The diurnal cycle and weather sequences from the baseline period are assumed to persist under future…
Limited to China: The bias-corrected dataset covers mainland China only.
Baseline period matters: The CMFD/MSWX forcing used as baseline determines the sub-daily variability. A longer baseline (e.g., 10+ years)…
Calibration recommended: Uncalibrated VIC amplifies projection errors. Relative changes (%) are more robust than absolute values.

What it can do on your machine

Read from SKILL.md and the folder at commit 889a6e7. 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 script files (Python, from the files we listed), which the agent can run.
Shell commands in SKILL.md call:
- python
- python3
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

Climate Projection loads about 3.9k tokens when it runs. Until then it costs about 67 tokens; SKILL.md has 1,234 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~67
When it runs · the whole SKILL.md, loaded when a task matches: ~3.9k

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); files beside SKILL.md are not scanned.

SKILL.md

The full file from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation at commit 889a6e7, republished under its MIT licence (© lzwei196). 1,234 words, ~3,871 tokens.

Download SKILL.mdSave it as .claude/skills/climate-projection/SKILL.md (or your agent's skills folder). This skill also uses 21 other files; get the full folder from GitHub.

name: climate-projection
description: Climate change impact assessment using CMIP6 data. Two extraction paths — China (26 models, local files) or Global (34 models, NASA NEX-GDDP-CMIP6 API). Computes delta-change signals, generates future VIC forcing, runs multi-model ensemble analysis.

MANDATORY EXECUTION POLICY — READ BEFORE PROCEEDING

You MUST run the actual model binary or package described in this document. If the model fails to import, compile, or execute, you MUST:

Check diagnostics/triplets.yaml for a matching error pattern

Try the fix suggested in the triplet's remedy section

If still failing, report the error to the user with full details

You MUST NOT substitute a simplified Python formula, regression equation, or hand-coded approximation in place of the real model. Doing so produces scientifically invalid results and defeats the purpose of the KI.

Before starting, run: python preflight_check.py (in this KI directory) to verify that the model binary/package and required data are available.

DEBUGGING PROTOCOL — When something goes wrong, follow this order:

Check triplets — diagnostics/triplets.yaml may already cover this error

Read official docs — The model's own documentation for expected formats/units

Find working examples — Check outputs/ or the model's shipped test data

Fix the tool — With knowledge of what "correct" looks like

Do NOT write custom debug scripts. The answers are in the docs and examples.

<!-- KI-MAP:BEGIN (projected by generate_skill_map.py — edit the KI, not this table) -->

KI map — what to read, and when

when you need	read	why
FIRST, always	`preflight_check.py`	run it (`python preflight_check.py`): proves env/binary/data are usable and emits a machine-readable `PREFLIGHT_REPORT=` line. Do not debug a run that never had a healthy environment.
to run the pipeline stages	`tools/` (5 tools)	the executable pipeline. Read each tool's argparse (`--help`) before composing a command; SKILL.md's stage table says which tool serves which stage.
before running a stage	`docs/s_.md` (4 stage docs)	per-stage procedure, verification and traps — the how-to that SKILL.md's overview compresses.
on ANY error, before debugging	`diagnostics/triplets.yaml` (10 entries)	symptom → diagnosis → remedy for this model's known failure modes. Check here FIRST; the answer usually exists. Never renumber or rewrite entries.
to know what an output IS	`dag.yaml`	the model's identity: every output's medium, units, `validation_rank` (1 = the headline variable) and observability. Scoring and obs-binding read THIS — when asked 'what does this model predict', the dag is the answer, not a guess.
when building inputs / parsing outputs	`docs/format_spec.yaml`	exact I/O shapes + `known_issues`, projected from dag + triplets. Regenerate with `ki_tools_common/generate_format_spec.py` after changing either — never hand-edit.
for claims and thresholds	`docs/gathered_papers.json` (21 papers) + `docs/papers_index.md`	the literature this KI is judged by; each entry's `text_path` is fetched full text in the central paper cache. `role: benchmark` marks the model's own skill paper.
for a machine-readable summary	`knowledge_infrastructure.yaml`	the manifest (package, pipeline, validation tier, counts) — projected by `ki_tools_common/generate_ki_manifest.py`; regenerate after structural changes, never hand-edit.

Projected 2026-08-17 from the KI's actual contents — 8 components present. Refresh: python3 ki_tools_common/generate_skill_map.py --ki_dir <this KI>.

<!-- KI-MAP:END -->

<!-- KI-TOOL-INDEX:BEGIN (projected by generate_skill_map.py — the discoverability contract: every public tool, exact path; PURPOSE stays human-authored elsewhere) -->

Executable tool index (projected — complete by construction)

Every public tool in this KI, by exact path. What each is FOR lives in the human-written Tool Inventory above; --help on any of these prints its arguments.

tool (exact path)	invocation
`tools/s1_extract_cmip/extract_cmip6_basin.py`	`KISSPATH_PYTHON_ENV/bin/python {KI}/tools/s1_extract_cmip/extract_cmip6_basin.py --help`
`tools/s1_extract_cmip/fetch_nex_gddp_global.py`	`KISSPATH_PYTHON_ENV/bin/python {KI}/tools/s1_extract_cmip/fetch_nex_gddp_global.py --help`
`tools/s2_compute_deltas/compute_climate_deltas.py`	`KISSPATH_PYTHON_ENV/bin/python {KI}/tools/s2_compute_deltas/compute_climate_deltas.py --help`
`tools/s3_apply_deltas/apply_deltas_forcing.py`	`KISSPATH_PYTHON_ENV/bin/python {KI}/tools/s3_apply_deltas/apply_deltas_forcing.py --help`
`tools/s3_apply_deltas/convert_projected_forcing.py`	`KISSPATH_PYTHON_ENV/bin/python {KI}/tools/s3_apply_deltas/convert_projected_forcing.py --help`

5 public tools; _-prefixed helpers and packaging files excluded.

<!-- KI-TOOL-INDEX:END -->

Data Preparation

Forcing data

Data Sources: Use from ki_tools_common.load_forcing import load_daily_forcing for CMFD/MSWX/NASA POWER.

Data Validation Reference: Framework models use data from the coupled models. See data_ki/CMIP6/SKILL.md for CMIP6 projection data documentation.

Climate Change Projection — Knowledge Infrastructure

Part of HydroCraft — AI-driven distributed hydrological simulation framework by the Jianyun Zhang Research Group.

This knowledge infrastructure enables an AI agent to autonomously run climate change impact assessments on any basin already set up in HydroCraft. It takes a calibrated (or uncalibrated) VIC model and produces projected future hydrology under CMIP6 climate scenarios.

When to Use This Skill

Use this skill after the VIC model has been set up and (ideally) calibrated for a basin. It is the natural next step:

VIC Setup → Calibration → Climate Change Projection ← YOU ARE HERE

The user may ask for this by saying:

"Run climate change projections"
"What will discharge look like under SSP2-4.5?"
"Climate change impact on this basin"
"Future hydrology" / "CMIP6 analysis"

Pipeline Overview

Stage	Tool	Skill Document	Description
S1	`extract_cmip6_basin` (China) OR `fetch_nex_gddp_global` (global)	`docs/s1_extract_cmip_skill.md`	Extract CMIP6 data for basin grid cells
S2	`compute_climate_deltas`	`docs/s2_compute_deltas_skill.md`	Compute monthly change factors (future vs historical)
S3	`apply_deltas_forcing`	`docs/s3_apply_deltas_skill.md`	Apply deltas to baseline CMFD/MSWX forcing
S4	(VIC + routing from baseline)	`docs/s4_ensemble_analysis_skill.md`	Run VIC ensemble & compare historical vs future

Dependencies: S1 → S2 → S3 → S4. Each stage must complete before the next begins.

Show full SKILL.md (522 more words)Show less

Choosing an Extraction Method (S1)

Method	Script	Coverage	Models	When to use
China local	`extract_cmip6_basin.py`	China only	26	Chinese basins (fastest, ~3 min)
Global API	`fetch_nex_gddp_global.py`	Worldwide	34	Any basin, no local data needed (~15 min)

Both produce identical output format — downstream tools (S2-S4) work unchanged.

Quick Start

Option A: China (local files)

bash

source KISSPATH_PYTHON_ENV/bin/activate
BASIN="bengbu"
MODEL="ACCESS-CM2"
SSP="245"

# S1: Extract CMIP6 data (historical + future)
python skills/climate-projection/tools/s1_extract_cmip/extract_cmip6_basin.py \
  KISSPATH_DATA/CMIP_China/Cmip6BaisCorrect_for_China \
  outputs/${BASIN}/vic_temp/grid/basin_grid.nc \
  ${MODEL} r1 outputs/${BASIN}/climate_projection/cmip6_extracted ${BASIN}

python skills/climate-projection/tools/s1_extract_cmip/extract_cmip6_basin.py \
  KISSPATH_DATA/CMIP_China/Cmip6BaisCorrect_for_China \
  outputs/${BASIN}/vic_temp/grid/basin_grid.nc \
  ${MODEL} ${SSP} outputs/${BASIN}/climate_projection/cmip6_extracted ${BASIN}

# S2: Compute deltas (1981-2010 baseline vs 2041-2070 future)
python skills/climate-projection/tools/s2_compute_deltas/compute_climate_deltas.py \
  outputs/${BASIN}/climate_projection/cmip6_extracted \
  outputs/${BASIN}/climate_projection/cmip6_extracted \
  ${MODEL} ${SSP} ${BASIN} 1981-2010 2041-2070 \
  outputs/${BASIN}/climate_projection/deltas

# S3: Apply deltas to baseline forcing
python skills/climate-projection/tools/s3_apply_deltas/apply_deltas_forcing.py \
  outputs/${BASIN}/vic_temp/forcing/forcing_1d \
  outputs/${BASIN}/climate_projection/deltas/${MODEL}_${SSP}_deltas_${BASIN}_2041-2070.nc \
  outputs/${BASIN}/vic_temp/grid/basin_grid.nc \
  outputs/${BASIN}/climate_projection/forcing_${MODEL}_${SSP} \
  ${BASIN} ${MODEL} ${SSP} 2041 2070

# S4: Run VIC + routing with projected forcing (see s4 skill document)

Option B: Global (NASA NEX-GDDP-CMIP6 API, any basin worldwide)

bash

source KISSPATH_PYTHON_ENV/bin/activate
BASIN="koksilah"
MODEL="ACCESS-CM2"

# S1: Fetch CMIP6 data via THREDDS (no local files needed)
python skills/climate-projection/tools/s1_extract_cmip/fetch_nex_gddp_global.py \
  --grid_nc outputs/${BASIN}/vic_temp/grid/basin_grid.nc \
  --model ${MODEL} --scenario historical --years 1981-2010 \
  --output_dir outputs/${BASIN}/climate_projection/cmip6_extracted \
  --basin_name ${BASIN}

python skills/climate-projection/tools/s1_extract_cmip/fetch_nex_gddp_global.py \
  --grid_nc outputs/${BASIN}/vic_temp/grid/basin_grid.nc \
  --model ${MODEL} --scenario ssp245 --years 2041-2070 \
  --output_dir outputs/${BASIN}/climate_projection/cmip6_extracted \
  --basin_name ${BASIN}

# S2-S4: Same as Option A (output format is identical)

# Multi-model ensemble (recommended 5 models):
python skills/climate-projection/tools/s1_extract_cmip/fetch_nex_gddp_global.py \
  --grid_nc outputs/${BASIN}/vic_temp/grid/basin_grid.nc \
  --models recommended --scenario ssp245 --years 2041-2070 \
  --output_dir outputs/${BASIN}/climate_projection/cmip6_extracted \
  --basin_name ${BASIN}

CMIP6 Data Reference

Location

KISSPATH_DATA/CMIP_China/Cmip6BaisCorrect_for_China/

Structure

Cmip6BaisCorrect_for_China/
├── pr/               # Precipitation (mm/day)
│   ├── r1/           # Historical (1961-2014)
│   ├── 126/          # SSP1-2.6 (2015-2099)
│   ├── 245/          # SSP2-4.5 (2015-2099)
│   └── 585/          # SSP5-8.5 (2015-2099)
├── tasmax/            # Daily max temperature (deg C)
│   └── (same structure)
└── tasmin/            # Daily min temperature (deg C)
    └── (same structure)

File Format

Tab-separated text, ~650 MB per file
Row 1: NaN NaN NaN [longitudes for 4,163 cells]
Row 2: NaN NaN NaN [latitudes for 4,163 cells]
Row 3+: Year Month Day [daily values for 4,163 cells]
Coverage: China (73.75-135.25E, 15.25-53.75N), 0.25-degree grid
Units: already bias-corrected, °C for temperature, mm/day for precipitation

Available Models (26 with all 3 variables)

ACCESS-CM2, ACCESS-ESM1-5, BCC-CSM2-MR, CanESM5, CESM2, CMCC-ESM2, CNRM-ESM2-1, EC-Earth3, EC-Earth3-Veg, EC-Earth3-Veg-LR, FGOALS-g3, GFDL-ESM4, INM-CM4-8, INM-CM5-0, IPSL-CM6A-LR, KIOST-ESM, MIROC6, MPI-ESM1-2-HR, MPI-ESM1-2-LR, MRI-ESM2-0, NESM3, NorESM2-LM, NorESM2-MM, TaiESM1, UKESM1-0-LL, CNRM-CM6-1 (pr only — has tasmax/tasmin too), KACE-1-0-G (pr only in some directories)

Recommended 5-model ensemble: ACCESS-CM2, BCC-CSM2-MR, EC-Earth3, MIROC6, MRI-ESM2-0

Scenarios

Code	CMIP6 Name	Period	Radiative Forcing	Description
`r1`	Historical	1961-2014	Observed	Reference baseline
`126`	SSP1-2.6	2015-2099	2.6 W/m²	Sustainability (Paris-aligned)
`245`	SSP2-4.5	2015-2099	4.5 W/m²	Middle of the road
`585`	SSP5-8.5	2015-2099	8.5 W/m²	Fossil-fuel intensive

Critical Domain Knowledge

Why Delta Change Method?

VIC needs 7 forcing variables (temp, prec, pres, srad, lrad, wind, shum), but CMIP6 only provides 3 (pr, tasmax, tasmin). The delta-change method preserves all 7 baseline variables while incorporating projected climate change:

Temperature: Additive delta → T_future = T_baseline + delta_T
Precipitation: Multiplicative ratio → P_future = P_baseline × ratio_P
Other variables: Unchanged from baseline (wind, pressure, radiation, humidity change less and are not available from CMIP6)

Key Assumptions

Stationarity of sub-daily patterns: The diurnal cycle and weather sequences from the baseline period are assumed to persist under future climate. Only monthly means change.
Limited to China: The bias-corrected dataset covers mainland China only.
Baseline period matters: The CMFD/MSWX forcing used as baseline determines the sub-daily variability. A longer baseline (e.g., 10+ years) is more robust.
Calibration recommended: Uncalibrated VIC amplifies projection errors. Relative changes (%) are more robust than absolute values.

Tools Reference

Stage	Tool ID	Script Path	Purpose
S1	extract_cmip6_basin	`tools/s1_extract_cmip/extract_cmip6_basin.py`	Extract CMIP6 data for basin cells
S2	compute_climate_deltas	`tools/s2_compute_deltas/compute_climate_deltas.py`	Monthly delta computation
S3	apply_deltas_forcing	`tools/s3_apply_deltas/apply_deltas_forcing.py`	Apply deltas to baseline forcing
S4	(uses VIC + routing tools)	(from vic-auto-run and routing-run skills)	Run model and analyse results

Error Handling

When an error occurs, look up the symptom in diagnostics/triplets.yaml. Key triplets:

ID	Severity	Summary
dt_cc_001	fatal	Basin outside China — no CMIP6 coverage
dt_cc_002	fatal	Model name mismatch — file not found
dt_cc_003	silent	Wrong column matching — bad coordinate precision
dt_cc_004	silent	Deltas are zero — historical/future files confused
dt_cc_005	degraded	Extreme precipitation ratio in dry months
dt_cc_006	fatal	VIC time range doesn't match projected forcing
dt_cc_007	silent	Pass-through variables (wind, pres) missing in output
dt_cc_008	degraded	Uncalibrated parameters amplify projection errors
dt_cc_009	fatal	Memory error reading large CMIP6 files

Output Directory Structure

outputs/{basin}/climate_projection/
├── cmip6_extracted/          # S1: Raw CMIP6 data per model/scenario/variable
│   ├── ACCESS-CM2_r1_pr_{basin}.nc
│   ├── ACCESS-CM2_245_pr_{basin}.nc
│   └── ...
├── deltas/                   # S2: Monthly change factors
│   ├── ACCESS-CM2_245_deltas_{basin}_2041-2070.nc
│   └── ...
├── forcing_{MODEL}_{SSP}/    # S3: Projected forcing (forcing_1d format)
│   ├── temp_cmfd_2041.nc
│   └── ...
├── forcing_final_{MODEL}_{SSP}/  # S3b: VIC ASCII forcing
│   ├── {prefix}_31.1250_115.6250
│   └── ...
├── vic_result_{MODEL}_{SSP}/ # S4: VIC output
├── routing_{MODEL}_{SSP}/    # S4: Routing output
└── ensemble_comparison.png   # S4: Multi-model comparison plot

This knowledge infrastructure was built using the Knowledge Dissection Toolkit (Zhang et al., Nature, under review). 3 validated tools | 4 skill documents | 9 diagnostic triplets | 4 pipeline stages

Files

SKILL.md and 21 other files in models/Climate_Projection of lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.

SKILL.md
dag.yaml
diagnostics/error_log.yaml
diagnostics/format_transformations.yaml
diagnostics/triplets.yaml
docs/REFERENCES.md
docs/format_spec.yaml
docs/papers.json
docs/s1_extract_cmip_skill.md
docs/s2_compute_deltas_skill.md
docs/s3_apply_deltas_skill.md
docs/s4_ensemble_analysis_skill.md
knowledge_infrastructure.yaml
preflight_check.py
tools/s1_extract_cmip/extract_cmip6_basin.py
tools/s1_extract_cmip/fetch_nex_gddp_global.py
tools/s2_compute_deltas
… and 5 more

Open the folder on GitHubat commit 889a6e7

Compare with similar skills

Climate Projection 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.

Climate Projection compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Climate Projection this skilllzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation	201	—	~3.9k	Automated safety check: Pass	MIT	4 days ago
MCP Server Builderanthropics/skills	180k	63 repos	~2.3k	Automated safety check: Pass	Apache-2.0	yesterday
PDF Processinganthropics/skills	180k	47 repos	~2k	Automated safety check: Pass	Proprietary	yesterday
NotebookLM Research AssistantPleasePrompto/notebooklm-skill	7.8k	14 repos	~2.4k	Automated safety check: Notes	MIT	1 mo ago
Manim Video Productionbrowser-use/video-use	29k	6 repos	~3k	Automated safety check: Pass	MIT	2 days ago
PPT Masterhugohe3/ppt-master	59k	1 repos	~2.5k	Automated safety check: Pass	MIT	3 days ago

Similar skills

MCP Server Builder
anthropics/skills
Official
Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.
180k GitHub starsUsed in 63 repos~2.3k tokens
Agent WorkflowsAuto-check passed
PDF Processing
anthropics/skills
Official
Handles everyday PDF jobs in Python and on the command line: extract text and tables, merge, split, rotate, watermark, fill forms, encrypt and OCR.
180k GitHub starsUsed in 47 repos~2k tokens
Documents & OfficeAuto-check passed
NotebookLM Research Assistant
PleasePrompto/notebooklm-skill
Lets Claude Code ask questions of your Google NotebookLM notebooks through browser automation and return answers grounded in your uploaded sources.
7.8k GitHub starsUsed in 14 repos~2.4k tokens
Knowledge ManagementAuto-check: notes
Manim Video Production
browser-use/video-use
Produces math and technical explainer videos with Manim Community Edition: concept animations, equation derivations, algorithm walkthroughs and data stories.
29k GitHub starsUsed in 6 repos~3k tokens
Media & CreativeAuto-check passed
PPT Master
hugohe3/ppt-master
Generates editable PowerPoint decks, rebuilds slides from images, fills .pptx templates and polishes existing presentations through routed workflows.
59k GitHub starsUsed in 1 repo~2.5k tokens
Documents & OfficeAuto-check passed
Scikit Learn
zLanqing/codex-claude-academic-skills
Machine learning in Python with scikit-learn. An agent skill from zLanqing/codex-claude-academic-skills.
4.7k GitHub starsUsed in 16 repos~3.9k tokens
Data & AnalyticsAuto-check passed

More from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation

Cama Flood Integration
lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation
CaMa-Flood v4.20 river routing and floodplain model. An agent skill from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation.
201 GitHub stars~7.6k tokensUpdated 4 days ago
Auto-check: notes

Works with

Python

Questions about Climate Projection

What does Climate Projection do?

Climate change impact assessment using CMIP6 data. An agent skill from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation. Climate Projection is an agent skill from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation. Climate change impact assessment using CMIP6 data.

How do I install Climate Projection in Claude Code?

Run `npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a claude-code`. Or copy the skill folder (models/Climate_Projection in lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation) into .claude/skills/climate-projection in your project. Claude Code loads it when a task matches its description.

How do I install Climate Projection in Codex?

Run `npx skills add lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a codex`. Or copy the skill folder (models/Climate_Projection in lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation) into .agents/skills/climate-projection in your project. Codex loads it when a task matches its description.

Can I use Climate Projection 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 lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation --skill climate-projection -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/climate-projection, .gemini/skills/climate-projection, .github/skills/climate-projection and .opencode/skills/climate-projection in your project.

What does Climate Projection need to run?

Going by SKILL.md and its folder, Climate Projection needs Python for the scripts in its folder and the command-line tools its instructions call (python and python3). Our summary lists: Python 3.

Does Climate Projection 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 Climate Projection 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. Review the folder before installing.

What licence does Climate Projection use?

Climate Projection 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 Climate Projection use?

About 3.9k tokens (SKILL.md is roughly 15k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Climate Projection?

Skills that share tags, products or a category with Climate Projection: MCP Server Builder (anthropics/skills, 180k stars), PDF Processing (anthropics/skills, 180k stars), NotebookLM Research Assistant (PleasePrompto/notebooklm-skill, 7.8k stars) and Manim Video Production (browser-use/video-use, 29k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Climate Projection?

lzwei196 (a GitHub user) maintains it in lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation, which has 201 GitHub stars. The repository holds 2 skills in this directory. The repository was last updated on October 7, 2026.

Source: lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Climate Projection

Facts

At a glance

What it does

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

KI map — what to read, and when

Executable tool index (projected — complete by construction)

Data Preparation

Forcing data

Climate Change Projection — Knowledge Infrastructure

When to Use This Skill

Pipeline Overview

Choosing an Extraction Method (S1)

Quick Start

Option A: China (local files)

Option B: Global (NASA NEX-GDDP-CMIP6 API, any basin worldwide)

CMIP6 Data Reference

Location

Structure

File Format

Available Models (26 with all 3 variables)

Scenarios

Critical Domain Knowledge

Why Delta Change Method?

Key Assumptions

Tools Reference

Error Handling

Output Directory Structure

Files

Compare with similar skills

Similar skills

MCP Server Builder

PDF Processing

NotebookLM Research Assistant

Manim Video Production

PPT Master

Scikit Learn

More from lzwei196/KISS-Knowledge-Infrastructure-for-Scientific-Simulation

Cama Flood Integration

Related

Questions about Climate Projection