Context Compression
guanyang/open-agent-hub
This skill should be used when long-running agent sessions need context compression, structured summarization, compaction, token-per-task optimization, or durable handoff summaries that preserve…
Choose the right LLM for a task by trading off quality, cost, latency, and constraints.
Install Model Selection Advisor
$ npx skills add mohitagw15856/pm-claude-skills --skill model-selection-advisor -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install mohitagw15856/pm-claude-skills model-selection-advisor --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/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/model-selection-advisor .claude/skills/model-selection-advisor && 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 "model-selection-advisor" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/model-selection-advisor into .claude/skills/model-selection-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-advisor", 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/mohitagw15856/pm-claude-skills/tree/main/skills/model-selection-advisorType 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 mohitagw15856/pm-claude-skills --skill model-selection-advisor -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install mohitagw15856/pm-claude-skills model-selection-advisor --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/model-selection-advisor .agents/skills/model-selection-advisor && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "model-selection-advisor" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/model-selection-advisor into .agents/skills/model-selection-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-advisor", 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 mohitagw15856/pm-claude-skills --skill model-selection-advisor -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install mohitagw15856/pm-claude-skills model-selection-advisor --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/model-selection-advisor .cursor/skills/model-selection-advisor && 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 "model-selection-advisor" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/model-selection-advisor into .cursor/skills/model-selection-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-advisor", 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/mohitagw15856/pm-claude-skills.git --path skills/model-selection-advisor--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 mohitagw15856/pm-claude-skills --skill model-selection-advisor -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install mohitagw15856/pm-claude-skills model-selection-advisor --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/model-selection-advisor .gemini/skills/model-selection-advisor && 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 "model-selection-advisor" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/model-selection-advisor into .gemini/skills/model-selection-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-advisor", 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 mohitagw15856/pm-claude-skills model-selection-advisorInstalls 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 mohitagw15856/pm-claude-skills --skill model-selection-advisor -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/model-selection-advisor .github/skills/model-selection-advisor && 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 "model-selection-advisor" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/model-selection-advisor into .github/skills/model-selection-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-advisor", 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 mohitagw15856/pm-claude-skills --skill model-selection-advisor -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install mohitagw15856/pm-claude-skills model-selection-advisor --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/mohitagw15856/pm-claude-skills.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/model-selection-advisor .opencode/skills/model-selection-advisor && 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 "model-selection-advisor" agent skill from https://github.com/mohitagw15856/pm-claude-skills/tree/main/skills/model-selection-advisor into .opencode/skills/model-selection-advisor/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "model-selection-advisor", 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
model-selection-advisor- GitHub stars
- 1.4k
- Token cost
- ~1.1k tokens
- SKILL.md length
- 581 words
- Files
- 1
- Skills in repo
- 1,348
- Repo updated
- First seen
- Licence
- MIT
At a glance
Choose the right LLM for a task by trading off quality, cost, latency, and constraints.
- Asked which model to use
- SKILL.md covers Working from a brief, Required Inputs, Output Format and Quality Checks, plus 3 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
- Whether to upgrade/downgrade a model
What it does
Model Selection Advisor is an agent skill from mohitagw15856/pm-claude-skills. Choose the right LLM for a task by trading off quality, cost, latency, and constraints. Use when asked which model to use, whether to upgrade/downgrade a model, how to cut LLM costs without hurting quality, or to justify a model choice. Produces a recommendation with the decision criteria, a per-option comparison, a routing strategy (cheap-by-default, escalate when needed), and how to validate the choice with an 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 AI & LLM Engineering, covering LLM cost and token optimization and Trading and backtesting. The repository describes itself as: 1255 professional Agent Skills for Claude, ChatGPT, Gemini, Cursor & Codex — PRDs, postmortems, leases, medical bills, layoffs, go-bags, new countries. Plain markdown, MIT, in… The licence is MIT.
When your agent uses it
- Asked which model to use
- Whether to upgrade/downgrade a model
- How to cut LLM costs without hurting quality
- Justify a model choice
Example prompts
- “/model-selection-advisor”
What it can do on your machine
Read from SKILL.md and the folder at commit 1cbf1f0. 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
No scripts in the folder and no shell commands in SKILL.md.
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
Model Selection Advisor loads about 1.1k tokens when it runs. Until then it costs about 111 tokens; SKILL.md has 581 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); files beside SKILL.md are not scanned.
SKILL.md
The full file from mohitagw15856/pm-claude-skills at commit 1cbf1f0, republished under its MIT licence (© mohitagw15856). 581 words, ~1,140 tokens.
Download SKILL.mdSave it as
.claude/skills/model-selection-advisor/SKILL.md (or your agent's skills folder).- name
- model-selection-advisor
- description
- Choose the right LLM for a task by trading off quality, cost, latency, and constraints. Use when asked which model to use, whether to upgrade/downgrade a model, how to cut LLM costs without hurting quality, or to justify a model choice. Produces a recommendation with the decision criteria, a per-option comparison, a routing strategy (cheap-by-default, escalate when needed), and how to validate the choice with an eval.
Model Selection Advisor Skill
The right model is rarely "the biggest one" or "the cheapest one" — it's the smallest model that clears the task's quality bar within its latency and cost budget, with a path to escalate the hard cases. This skill makes that trade-off explicit and defensible, and ties it to an eval so the choice is measured, not vibes.
Working from a brief
Given "what model should I use for summarising support tickets?", deliver a concrete recommendation anyway — infer the task's difficulty, volume, and latency sensitivity, label the assumptions, and recommend. Never hand back "it depends" with no pick; give a default and the condition under which you'd change it.
Required Inputs
Ask for these only if they aren't already provided (else infer and label):
- The task — what the model does, and an example input/output. How hard is it (extraction vs. reasoning vs. open-ended)?
- Quality bar — what "good enough" means, and the cost of a wrong answer.
- Volume & latency — requests/day and how fast a response must come back (interactive vs. batch).
- Constraints — budget, context-length needs, tool use, privacy/region, and whether outputs must be reproducible.
Output Format
Model Recommendation: [task]
1. Decision criteria — the 3–5 factors that actually decide it here, ranked (e.g. reasoning depth > latency > cost), with why.
2. Option comparison — the realistic candidates scored against the criteria. Keep it provider-agnostic in method; name a default family (e.g. the Claude family — a small/fast tier, a balanced tier, a frontier tier) and reason by tier, not a single hardcoded model, so the advice survives model releases.
| Option (tier) | Quality on this task | Latency | Relative cost | Fit |
|---|---|---|---|---|
| Small/fast | clears bar for easy cases | low | $ | default for the bulk |
| Balanced | clears bar for most cases | med | $$ | when small misses |
| Frontier | clears the hardest cases | higher | $$$ | escalation / eval judge |
3. Recommendation — the default model/tier, in one sentence, with the single reason.
4. Routing strategy — cheap-by-default with escalation: run the small tier first, detect low-confidence or hard cases (length, ambiguity, a validator/judge failing), and escalate those to a stronger tier. This usually beats picking one model for everything on both cost and quality.
5. Validation — how to confirm the choice: a small eval set scored per tier (pair with
eval-rubric-designer and ai-eval-plan),
and a cost/latency estimate at real volume (pair with llm-cost-latency-budget).
Show full SKILL.md (202 more words)Show less
Quality Checks
- The recommendation names a default model/tier and the condition that would change it
- Reasoning is by tier (small/balanced/frontier), not a single hardcoded model that dates quickly
- A routing/escalation strategy is considered, not just a single fixed choice
- The choice is tied to a measurable quality bar and an eval to verify it
- Cost and latency are estimated at real volume, not per single call
- Constraints (context length, privacy/region, reproducibility, tool use) are checked against the pick
Anti-Patterns
- Do not default to the biggest model "to be safe" — pay only for the capability the task needs
- Do not pick on price alone — a cheap model that fails the bar costs more in rework and trust
- Do not recommend without an eval to confirm the quality bar is actually met
- Do not hardcode a single model name as the answer — reason by tier and let the eval pick the current best in it
- Do not ignore the long tail — design for the hard cases via escalation, not by oversizing everything
Based On
Model-selection practice — quality/cost/latency trade-offs, tiered routing with escalation, and eval-driven validation.
Example Trigger Phrases
- "Which model to use?"
- "How to cut LLM costs without hurting quality?"
- "Justify a model choice."
© mohitagw15856, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/model-selection-advisor of mohitagw15856/pm-claude-skills.
Open the folder on GitHubat commit 1cbf1f0
Compare with similar skills
Model Selection Advisor 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 |
|---|---|---|---|---|---|---|
| Model Selection Advisor this skillmohitagw15856/pm-claude-skills | 1.4k | — | ~1.1k | Automated safety check: Pass | MIT | |
| Context Compressionguanyang/open-agent-hub | 977 | 2 repos | ~4.6k | Automated safety check: Pass | MIT | |
| Bounty Hunter1sadjlk/bounty-hunter-skill | 282 | 1 repos | ~761 | Automated safety check: Pass | MIT | |
| Skill Shortenerluongnv89/asm | 954 | — | ~3.8k | Automated safety check: Notes | MIT | |
| Fleet Auditoralexgreensh/token-optimizer | 2.5k | — | ~1.7k | Automated safety check: Pass | Custom licence | |
| Context Auditundefined-ui/second-brain-os | 1k | — | ~802 | Automated safety check: Pass | MIT |
Similar skills
Bounty Hunter
1sadjlk/bounty-hunter-skill
A professional AI bounty hunter persona named Atlas. An agent skill from 1sadjlk/bounty-hunter-skill.
Skill Shortener
luongnv89/asm
Refactor a too-long SKILL.md by progressive disclosure: measure token cost, classify every section KEEP/CUT/MOVE, shorten the body into references/ and scripts/, verify nothing was lost.
Fleet Auditor
alexgreensh/token-optimizer
Cross-system agent token/cost audit (Claude Code, Codex, OpenClaw, Hermes, OpenCode): idle burns, model misrouting, config bloat, with dollar savings.
Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
Headroom
momori777/Artemis
SmartCrusher + CCR context compression — crunch large JSON arrays, tool outputs, and search results to save tokens.
More from mohitagw15856/pm-claude-skills
All 1,348 skills in this repoCar Tco
mohitagw15856/pm-claude-skills
Compare the total cost of car ownership across buy-new, buy-used, lease, and keep-your-current-car — depreciation, insurance, maintenance ramp, and fuel over a real horizon, not just the monthly…
Cs Health Scorecard
mohitagw15856/pm-claude-skills
Build a customer health scorecard for a specific account. An agent skill from mohitagw15856/pm-claude-skills.
Exit Waterfall
mohitagw15856/pm-claude-skills
Compute who gets what at each exit price from a cap table — liquidation preferences, conversion points, and where the founders' share collapses.
Feature Prioritisation
mohitagw15856/pm-claude-skills
Apply prioritisation frameworks (RICE, MoSCoW, Kano, ICE, Opportunity Scoring) to rank features and backlog items.
Fire Number
mohitagw15856/pm-claude-skills
Compute a financial-independence (FIRE) target and years-to-reach with every assumption labeled as an assumption — plus a sensitivity table instead of a single false-precision answer.
Freelance Rate
mohitagw15856/pm-claude-skills
Derive a freelance day/hourly rate backwards from target income, honest billable utilization, overhead, and the self-employment tax premium — the arithmetic that proves a rate is not salary÷2000.
Related
Categories
Questions about Model Selection Advisor
What does Model Selection Advisor do?
Choose the right LLM for a task by trading off quality, cost, latency, and constraints. Model Selection Advisor is an agent skill from mohitagw15856/pm-claude-skills. Choose the right LLM for a task by trading off quality, cost, latency, and constraints.
When should I use Model Selection Advisor?
Model Selection Advisor fits situations like: asked which model to use; whether to upgrade/downgrade a model; how to cut LLM costs without hurting quality; justify a model choice.
How do I install Model Selection Advisor in Claude Code?
Run `npx skills add mohitagw15856/pm-claude-skills --skill model-selection-advisor -a claude-code`. Or copy the skill folder (skills/model-selection-advisor in mohitagw15856/pm-claude-skills) into .claude/skills/model-selection-advisor in your project. Claude Code loads it when a task matches its description.
How do I install Model Selection Advisor in Codex?
Run `npx skills add mohitagw15856/pm-claude-skills --skill model-selection-advisor -a codex`. Or copy the skill folder (skills/model-selection-advisor in mohitagw15856/pm-claude-skills) into .agents/skills/model-selection-advisor in your project. Codex loads it when a task matches its description.
Can I use Model Selection Advisor 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 mohitagw15856/pm-claude-skills --skill model-selection-advisor -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/model-selection-advisor, .gemini/skills/model-selection-advisor, .github/skills/model-selection-advisor and .opencode/skills/model-selection-advisor in your project.
What does Model Selection Advisor need to run?
SKILL.md names no scripts, command-line tools or credentials: Model Selection Advisor is instructions for the agent only.
Does Model Selection Advisor 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 Model Selection Advisor 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 Model Selection Advisor use?
Model Selection Advisor 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 Model Selection Advisor use?
About 1.1k tokens (SKILL.md is roughly 4.6k 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 Model Selection Advisor?
Skills that share tags, products or a category with Model Selection Advisor: Context Compression (guanyang/open-agent-hub, 977 stars), Bounty Hunter (1sadjlk/bounty-hunter-skill, 282 stars), Skill Shortener (luongnv89/asm, 954 stars) and Fleet Auditor (alexgreensh/token-optimizer, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Model Selection Advisor?
mohitagw15856 (a GitHub user) maintains it in mohitagw15856/pm-claude-skills, which has 1,433 GitHub stars. The repository holds 1,348 skills in this directory. The repository was last updated on October 8, 2026.
Source: mohitagw15856/pm-claude-skills on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.