Agent skill

Sft Cleanup Hf Only

by open-thoughts in open-thoughts/OpenThoughts-Agent

Clean up a completed NON-AGENTIC / HF-only SFT model — HF upload WITHOUT Supabase DB registration.

Apache-2.0Auto-check passedDocuments & Office

Install Sft Cleanup Hf Only

skills CLI

$ npx skills add open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a claude-code

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

GitHub CLI

$ gh skill install open-thoughts/OpenThoughts-Agent sft-cleanup-hf-only --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/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/sft-cleanup-hf-only .claude/skills/sft-cleanup-hf-only && 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 "sft-cleanup-hf-only" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/sft-cleanup-hf-only into .claude/skills/sft-cleanup-hf-only/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sft-cleanup-hf-only", 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/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/sft-cleanup-hf-only

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 open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a codex

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

GitHub CLI

$ gh skill install open-thoughts/OpenThoughts-Agent sft-cleanup-hf-only --agent codex

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

Manual copy

$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.agents/skills/sft-cleanup-hf-only .agents/skills/sft-cleanup-hf-only && 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 "sft-cleanup-hf-only" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/sft-cleanup-hf-only into .agents/skills/sft-cleanup-hf-only/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sft-cleanup-hf-only", 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 open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a cursor

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

GitHub CLI

$ gh skill install open-thoughts/OpenThoughts-Agent sft-cleanup-hf-only --agent cursor

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

Manual copy

$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.agents/skills/sft-cleanup-hf-only .cursor/skills/sft-cleanup-hf-only && 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 "sft-cleanup-hf-only" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/sft-cleanup-hf-only into .cursor/skills/sft-cleanup-hf-only/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sft-cleanup-hf-only", 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/open-thoughts/OpenThoughts-Agent.git --path .agents/skills/sft-cleanup-hf-only

--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 open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a gemini-cli

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

GitHub CLI

$ gh skill install open-thoughts/OpenThoughts-Agent sft-cleanup-hf-only --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/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.agents/skills/sft-cleanup-hf-only .gemini/skills/sft-cleanup-hf-only && 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 "sft-cleanup-hf-only" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/sft-cleanup-hf-only into .gemini/skills/sft-cleanup-hf-only/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sft-cleanup-hf-only", 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 open-thoughts/OpenThoughts-Agent sft-cleanup-hf-only

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 open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a github-copilot

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

Manual copy

$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .github/skills && cp -r skills-src/.agents/skills/sft-cleanup-hf-only .github/skills/sft-cleanup-hf-only && 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 "sft-cleanup-hf-only" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/sft-cleanup-hf-only into .github/skills/sft-cleanup-hf-only/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sft-cleanup-hf-only", 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 open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -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 open-thoughts/OpenThoughts-Agent sft-cleanup-hf-only --agent opencode

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

Manual copy

$ git clone --depth 1 https://github.com/open-thoughts/OpenThoughts-Agent.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.agents/skills/sft-cleanup-hf-only .opencode/skills/sft-cleanup-hf-only && 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 "sft-cleanup-hf-only" agent skill from https://github.com/open-thoughts/OpenThoughts-Agent/tree/main/.agents/skills/sft-cleanup-hf-only into .opencode/skills/sft-cleanup-hf-only/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "sft-cleanup-hf-only", 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: sft-cleanup-hf-only
GitHub stars: 301
Token cost: ~1.1k tokens
SKILL.md length: 425 words
Files: 1
Skills in repo: 44
Repo updated: Sep 28, 2026
First seen: Oct 7, 2026
Licence: Apache-2.0

At a glance

Clean up a completed NON-AGENTIC / HF-only SFT model — HF upload WITHOUT Supabase DB registration.

Works in 4 steps: Confirm HF-only completion. Check… → Cancel that cell's pending restart chain… → Prepare weights: 8B uses root… → …
A completed SFT cell belongs to an HF-only series (config enabledbregistration: false
SKILL.md covers When to use, Procedure (per completed cell) and Downstream chain (every sweep)
Calls hf and python; needs HF_TOKEN

What it does

Sft Cleanup Hf Only is an agent skill from open-thoughts/OpenThoughts-Agent. Clean up a completed NON-AGENTIC / HF-only SFT model — HF upload WITHOUT Supabase DB registration. The counterpart to sft-job-cleanup (which uploads AND registers). Use when a completed SFT cell belongs to an HF-only series (config enabledbregistration: false, or a known HF-only series like the Delphi 6279 54-grid): upload the weights to laion/ and STOP — do NOT run manualdbpush. Covers cell→hubmodelid resolution (incl. the Delphi launch54map.tsv), the Leonardo sbatch-tunnel upload, and the downstream eval…

Its SKILL.md is about 1.1k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Documents & Office, covering CSV and tabular files. It works with Supabase. The repository describes itself as: Data recipes and robust infrastructure for training AI agents. The licence is Apache-2.0.

When your agent uses it

A completed SFT cell belongs to an HF-only series (config enabledbregistration: false
A known HF-only series like the Delphi 6279 54-grid): upload the weights to laion/ and STOP — do NOT run manualdbpush

Example prompts

“/sft-cleanup-hf-only”

Requirements

Python 3

Workflow steps

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

Confirm HF-only completion. Check enable_db_registration: false (or Delphi delphi-*) and final training progress.
Cancel that cell's pending restart chain (squeue … | grep | grep PENDING | awk … | xargs -r scancel).
Prepare weights: 8B uses root model.safetensors; 32B/ZeRO-3 needs consolidation. Drop intermediate checkpoint-* and .cache.
Resolve hub_model_id

What it can do on your machine

Read from SKILL.md and the folder at commit 3bd1917. 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
Shell commands in SKILL.md call:
- hf
- python
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 these keys or tokens, usually read from environment variables:
- HF_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Sft Cleanup Hf Only loads about 1.1k tokens when it runs. Until then it costs about 152 tokens; SKILL.md has 425 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~152
When it runs · the whole SKILL.md, loaded when a task matches: ~1.1k

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 open-thoughts/OpenThoughts-Agent at commit 3bd1917, republished under its Apache-2.0 licence (© open-thoughts). 425 words, ~1,085 tokens.

Download SKILL.mdSave it as .claude/skills/sft-cleanup-hf-only/SKILL.md (or your agent's skills folder).

name: sft-cleanup-hf-only
description: Clean up a completed NON-AGENTIC / HF-only SFT model — HF upload WITHOUT Supabase DB registration. The counterpart to sft-job-cleanup (which uploads AND registers). Use when a completed SFT cell belongs to an HF-only series (config `enable_db_registration: false`, or a known HF-only series like the Delphi #6279 54-grid): upload the weights to laion/ and STOP — do NOT run manual_db_push. Covers cell→hub_model_id resolution (incl. the Delphi launch_54_map.tsv), the Leonardo sbatch-tunnel upload, and the downstream eval hand-off. For DB-registered models use sft-job-cleanup instead.

sft-cleanup-hf-only

Publish the completed HF-only SFT model without Supabase registration. Use sft-job-cleanup for registered SFT.

When to use

A completed SFT cell whose config sets enable_db_registration: false, OR a known HF-only series (Delphi #6279 delphi-* cells).
Discovered during a sweep, or "upload the completed Delphi cells (no DB)".
If it's a normal registered SFT → use sft-job-cleanup (don't skip the DB step there).

Procedure (per completed cell)

Confirm HF-only completion. Check enable_db_registration: false (or Delphi delphi-*) and final training progress.
Cancel that cell's pending restart chain (squeue … | grep <job> | grep PENDING | awk … | xargs -r scancel).
Prepare weights: 8B uses root model.safetensors; 32B/ZeRO-3 needs consolidation. Drop intermediate checkpoint-* and .cache.
Resolve hub_model_id:
- Delphi: name is laion/delphi-<base>-<recipe>_lr1e5-sft; the authoritative cell→hub_model_id↔jobid map is /leonardo_work/AIFAC_5C0_290/bfeuer00/experiments/delphi-prepared-tok/launch_54_map.tsv. Resolve from there (don't guess).
- Otherwise read the rendered launch config's hub_model_id.
- Qwen3.5: copy preprocessor_config.json from the base model into the checkpoint before upload. 4b. Check the tokenizer before upload: extra_special_tokens in tokenizer_config.json must be a dict, not a list (python -c "import json;d=json.load(open('<ckpt>/tokenizer_config.json'));assert isinstance(d.get('extra_special_tokens',{}),dict)"). If it is a list, set it to {} and re-save; the RL/SkyRL loader expects a dict.
Upload to HF (public default):
- Leonardo: use the sbatch compute-node + SSH-tunnel upload (.agents/ops/leonardo/ops.md "Leonardo HF Upload"; use hf upload, not upload-large-folder).
- Jupiter: login node has direct internet → hf upload in tmux.
- source "$DC_AGENT_SECRET_ENV" for HF_TOKEN (env var only — never inline).
Do not run manual_db_push.py.
Clean the cell's exp/checkpoint dir after the upload is verified (detached rm on GPFS; no du/find).
Verify: the laion/<name> repo exists with model.safetensors (>500MB) + tokenizer/config. Note the cell as done.

Show full SKILL.md (162 more words)Show less

Downstream chain (every sweep)

SFT completes → HF upload (this skill; no DB).
upload completes → eval-standard-launch on the series' eval grid for the newly-uploaded cell(s).
eval completes → record scores in the experiment tracker — for Delphi, append the cell's result to /Users/benjaminfeuer/Documents/experiments/active/delphi/rl-scaling-laws-6279/main_sft_evals/SCORES.md. Pull the score from the completed delphi-eval/<RUN>/ output + the eval job's metrics.

Skip work already done.

Delphi eval traps (carry into the eval hand-off)

HF_HUB_ENABLE_HF_TRANSFER MUST be 0/unset when pre-caching the -sft repos into $HF_HUB_CACHE for eval — hf_transfer isn't in the evalchemy env, so =1 leaves an EMPTY .incomplete blob (silent no-op). Verify the snapshot has model.safetensors (>500MB) before submitting.
The -sft repos ship the chat template as a separate chat_template.jinja file (NOT in tokenizer_config.json's chat_template key) — the eval sbatch's delphi_v0 override reads/replaces that file.
Per-cell TP must divide num_attention_heads: 9e18 heads=9→TP=1, 2e19 heads=11→TP=1, 3e19 heads=12→TP=2 (the sbatch's hardcoded TP=2 is WRONG for 9e18/2e19 — pass the optional TP_OVERRIDE 4th positional arg).

Full Delphi series data: project_delphi_sft_hf_only_no_db; upload mechanics: .agents/ops/leonardo/ops.md.

Files

Just SKILL.md in .agents/skills/sft-cleanup-hf-only of open-thoughts/OpenThoughts-Agent.

Open the folder on GitHubat commit 3bd1917

Compare with similar skills

Sft Cleanup Hf Only 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.

Sft Cleanup Hf Only compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Sft Cleanup Hf Only this skillopen-thoughts/OpenThoughts-Agent	301	—	~1.1k	Automated safety check: Pass	Apache-2.0	11 days ago
Linkedin Outreachgooseworks-ai/goose-skills	1.2k	1 repos	~4.4k	Automated safety check: Notes	MIT	yesterday
Data Table Managern8n-io/n8n	207k	—	~2.3k	Automated safety check: Pass	Custom licence	today
Instrument Data To Allotropeaws-samples/amazon-bedrock-agents-healthcare-lifesciences	274	2 repos	~2.7k	Automated safety check: Pass	Apache-2.0	8 days ago
Abuse Hunternexu-io/harness-engineering-guide	664	—	~1.9k	Automated safety check: Pass	MIT	5 mo ago
Markitshift-labs-ai/markit	1.3k	—	~299	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Linkedin Outreach
gooseworks-ai/goose-skills
End-to-end LinkedIn outreach campaign builder. An agent skill from gooseworks-ai/goose-skills.
1.2k GitHub starsUsed in 1 repo~4.4k tokens
Documents & OfficeAuto-check: notes
Data Table Manager
n8n-io/n8n
Official
Load before calling data-tables or parse-file. An agent skill from n8n-io/n8n.
207k GitHub stars~2.3k tokensUpdated today
Documents & OfficeAuto-check passed
Instrument Data To Allotrope
aws-samples/amazon-bedrock-agents-healthcare-lifesciences
Official
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV.
274 GitHub starsUsed in 2 repos~2.7k tokens
Documents & OfficeAuto-check passed
Abuse Hunter
nexu-io/harness-engineering-guide
Detect and investigate bulk registration abuse on SaaS platforms.
664 GitHub stars~1.9k tokensUpdated 5 mo ago
Documents & OfficeAuto-check passed
Markit
shift-labs-ai/markit
Convert files and URLs to Markdown. An agent skill from shift-labs-ai/markit.
1.3k GitHub stars~299 tokensUpdated 1 mo ago
Documents & OfficeAuto-check passed
Sector Analyst
tradermonty/claude-trading-skills
This skill should be used when analyzing sector rotation patterns and market cycle positioning.
3k GitHub starsUsed in 1 repo~2.3k tokens
Documents & OfficeAuto-check passed

More from open-thoughts/OpenThoughts-Agent

All 44 skills in this repo

Analyze Dataset Token Length
open-thoughts/OpenThoughts-Agent
Analyze the token length of an OT-Agent conversation-format (ShareGPT-style) dataset — the per-trace distribution (median/p90/max) and/or counts under a token threshold + a metadata predicate (e.g.
301 GitHub stars~1.5k tokensUpdated 11 days ago
Auto-check passed
Analyze Id Eval Ranking
open-thoughts/OpenThoughts-Agent
Given a list of models (HF name stubs) that have valid agentic ID eval scores in Supabase, build a ranking table: raw per-benchmark accuracy on the 3 ID benchmarks (SWE-Bench-100…
301 GitHub stars~3.1k tokensUpdated 11 days ago
Auto-check passed
Analyze Job History Iris
open-thoughts/OpenThoughts-Agent
Run the Iris harbor job-history analyzer (scripts/iris/analyzeirisharborjob.py) on a datagen/eval job and read its JSON sidecar for trustworthy throughput / preemption / productive-trial stats.
301 GitHub stars~2.9k tokensUpdated 11 days ago
Auto-check passed
Analyze Rl Behavior
open-thoughts/OpenThoughts-Agent
Run the full RL behavioral-analysis pipeline (scripts/analysis/analyzerlbehavior.py) on a trained RL model to understand WHAT changed vs its pre-RL baseline, WHY, whether it PERSISTS, and its EVAL…
301 GitHub stars~4.2k tokensUpdated 11 days ago
Auto-check passed
Analyze Training Run Iris
open-thoughts/OpenThoughts-Agent
Detailed health check for a Levanter/executor TRAINING run on the marin Iris cluster (e.g.
301 GitHub stars~2k tokensUpdated 11 days ago
Auto-check passed
Code Create Staged Plan
open-thoughts/OpenThoughts-Agent
DESIGN a non-trivial codebase change (Harbor / MarinSkyRL / vLLM / OT-Agent / LLaMA-Factory) as a dependency-ordered STAGED PLAN before writing code — a feature port, a multi-step fix with parity…
301 GitHub stars~1.5k tokensUpdated 11 days ago
Auto-check passed

Works with

Supabase

Questions about Sft Cleanup Hf Only

What does Sft Cleanup Hf Only do?

Clean up a completed NON-AGENTIC / HF-only SFT model — HF upload WITHOUT Supabase DB registration. Sft Cleanup Hf Only is an agent skill from open-thoughts/OpenThoughts-Agent. Clean up a completed NON-AGENTIC / HF-only SFT model — HF upload WITHOUT Supabase DB registration.

When should I use Sft Cleanup Hf Only?

Sft Cleanup Hf Only fits situations like: A completed SFT cell belongs to an HF-only series (config enabledbregistration: false; A known HF-only series like the Delphi 6279 54-grid): upload the weights to laion/ and STOP — do NOT run manualdbpush.

How do I install Sft Cleanup Hf Only in Claude Code?

Run `npx skills add open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a claude-code`. Or copy the skill folder (.agents/skills/sft-cleanup-hf-only in open-thoughts/OpenThoughts-Agent) into .claude/skills/sft-cleanup-hf-only in your project. Claude Code loads it when a task matches its description.

How do I install Sft Cleanup Hf Only in Codex?

Run `npx skills add open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a codex`. Or copy the skill folder (.agents/skills/sft-cleanup-hf-only in open-thoughts/OpenThoughts-Agent) into .agents/skills/sft-cleanup-hf-only in your project. Codex loads it when a task matches its description.

Can I use Sft Cleanup Hf Only 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 open-thoughts/OpenThoughts-Agent --skill sft-cleanup-hf-only -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/sft-cleanup-hf-only, .gemini/skills/sft-cleanup-hf-only, .github/skills/sft-cleanup-hf-only and .opencode/skills/sft-cleanup-hf-only in your project.

What does Sft Cleanup Hf Only need to run?

Going by SKILL.md and its folder, Sft Cleanup Hf Only needs the command-line tools its instructions call (hf and python) and credentials named HF_TOKEN. Our summary lists: Python 3.

Does Sft Cleanup Hf Only 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 Sft Cleanup Hf Only 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 Sft Cleanup Hf Only use?

Sft Cleanup Hf Only is published under the Apache-2.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Sft Cleanup Hf Only use?

About 1.1k tokens (SKILL.md is roughly 4.3k 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 Sft Cleanup Hf Only?

Skills that share tags, products or a category with Sft Cleanup Hf Only: Linkedin Outreach (gooseworks-ai/goose-skills, 1.2k stars), Data Table Manager (n8n-io/n8n, 207k stars), Instrument Data To Allotrope (aws-samples/amazon-bedrock-agents-healthcare-lifesciences, 274 stars) and Abuse Hunter (nexu-io/harness-engineering-guide, 664 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Sft Cleanup Hf Only?

open-thoughts (a GitHub organization) maintains it in open-thoughts/OpenThoughts-Agent, which has 301 GitHub stars. The repository holds 44 skills in this directory. The repository was last updated on September 28, 2026.

Source: open-thoughts/OpenThoughts-Agent on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Sft Cleanup Hf Only

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

Workflow steps

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

sft-cleanup-hf-only

When to use

Procedure (per completed cell)

Downstream chain (every sweep)

Delphi eval traps (carry into the eval hand-off)

Files

Compare with similar skills

Similar skills

More from open-thoughts/OpenThoughts-Agent

Related

Questions about Sft Cleanup Hf Only