Gptqmodel Tokenizer Normalization
ModelCloud/GPTQModel
Diagnose and correct GPT-QModel tokenizer initialization, tokenization normalization, special-token handling, prompt rendering, and chat-template problems.
Given a .mlir file (or a directory of .mlir files) with TTIR ops, run the same TTIR normalization passes as D2MFrontendPipeline before D2M, then produce per-file outputs: preprocessed.mlir…
Install Ttir Model Op Analysis
$ npx skills add tenstorrent/tt-mlir --skill ttir-model-op-analysis -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install tenstorrent/tt-mlir ttir-model-op-analysis --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/tenstorrent/tt-mlir.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/d2m-model-op-analysis .claude/skills/ttir-model-op-analysis && 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 "ttir-model-op-analysis" agent skill from https://github.com/tenstorrent/tt-mlir/tree/main/.claude/skills/d2m-model-op-analysis into .claude/skills/ttir-model-op-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ttir-model-op-analysis", 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/tenstorrent/tt-mlir/tree/main/.claude/skills/d2m-model-op-analysisType 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 tenstorrent/tt-mlir --skill ttir-model-op-analysis -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install tenstorrent/tt-mlir ttir-model-op-analysis --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tenstorrent/tt-mlir.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/d2m-model-op-analysis .agents/skills/ttir-model-op-analysis && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "ttir-model-op-analysis" agent skill from https://github.com/tenstorrent/tt-mlir/tree/main/.claude/skills/d2m-model-op-analysis into .agents/skills/ttir-model-op-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ttir-model-op-analysis", 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 tenstorrent/tt-mlir --skill ttir-model-op-analysis -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install tenstorrent/tt-mlir ttir-model-op-analysis --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tenstorrent/tt-mlir.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/d2m-model-op-analysis .cursor/skills/ttir-model-op-analysis && 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 "ttir-model-op-analysis" agent skill from https://github.com/tenstorrent/tt-mlir/tree/main/.claude/skills/d2m-model-op-analysis into .cursor/skills/ttir-model-op-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ttir-model-op-analysis", 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/tenstorrent/tt-mlir.git --path .claude/skills/d2m-model-op-analysis--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 tenstorrent/tt-mlir --skill ttir-model-op-analysis -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install tenstorrent/tt-mlir ttir-model-op-analysis --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tenstorrent/tt-mlir.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/d2m-model-op-analysis .gemini/skills/ttir-model-op-analysis && 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 "ttir-model-op-analysis" agent skill from https://github.com/tenstorrent/tt-mlir/tree/main/.claude/skills/d2m-model-op-analysis into .gemini/skills/ttir-model-op-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ttir-model-op-analysis", 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 tenstorrent/tt-mlir ttir-model-op-analysisInstalls 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 tenstorrent/tt-mlir --skill ttir-model-op-analysis -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/tenstorrent/tt-mlir.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/d2m-model-op-analysis .github/skills/ttir-model-op-analysis && 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 "ttir-model-op-analysis" agent skill from https://github.com/tenstorrent/tt-mlir/tree/main/.claude/skills/d2m-model-op-analysis into .github/skills/ttir-model-op-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ttir-model-op-analysis", 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 tenstorrent/tt-mlir --skill ttir-model-op-analysis -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install tenstorrent/tt-mlir ttir-model-op-analysis --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/tenstorrent/tt-mlir.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/d2m-model-op-analysis .opencode/skills/ttir-model-op-analysis && 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 "ttir-model-op-analysis" agent skill from https://github.com/tenstorrent/tt-mlir/tree/main/.claude/skills/d2m-model-op-analysis into .opencode/skills/ttir-model-op-analysis/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "ttir-model-op-analysis", 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
ttir-model-op-analysis- GitHub stars
- 314
- Token cost
- ~1.8k tokens
- SKILL.md length
- 488 words
- Files
- 1
- Skills in repo
- 9
- Repo updated
- First seen
- Licence
- Apache-2.0
At a glance
Given a .mlir file (or a directory of .mlir files) with TTIR ops, run the same TTIR normalization passes as D2MFrontendPipeline before D2M, then produce per-file outputs: preprocessed.mlir…
- Works in 2 steps: Run the frontend TTIR normalization… → Fill the report and ops.mlir
- Tasks that involve Database schema design
- SKILL.md covers Step 1: Run the frontend TTIR…, Step 2: Fill the report and… and Next: compile/run the snippets
- Calls python
What it does
Ttir Model Op Analysis is an agent skill from tenstorrent/tt-mlir. Given a .mlir file (or a directory of .mlir files) with TTIR ops, run the same TTIR normalization passes as D2MFrontendPipeline before D2M, then produce per-file outputs: preprocessed.mlir, ttir-op-report.txt (op counts from normalized IR), and ops.mlir (one func per unique op configuration, golden-style). Optional: per-pass IR dumps.
Its SKILL.md is about 1.8k 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 Databases, covering Database schema design. It works with vLLM. The repository describes itself as: Tenstorrent MLIR compiler. The licence is Apache-2.0.
When your agent uses it
- Tasks that involve Database schema design
Example prompts
- “/ttir-model-op-analysis”
Requirements
- Python 3
Workflow steps
2 steps, taken from the step headings in SKILL.md.
What it can do on your machine
Read from SKILL.md and the folder at commit 78b7044. 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:
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 no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Ttir Model Op Analysis loads about 1.8k tokens when it runs. Until then it costs about 93 tokens; SKILL.md has 488 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 tenstorrent/tt-mlir at commit 78b7044, republished under its Apache-2.0 licence (© tenstorrent). 488 words, ~1,834 tokens.
Download SKILL.mdSave it as
.claude/skills/ttir-model-op-analysis/SKILL.md (or your agent's skills folder).- name
- ttir-model-op-analysis
- description
- Given a `.mlir` file (or a directory of `.mlir` files) with TTIR ops, run the same TTIR normalization passes as `D2MFrontendPipeline` before D2M, then produce per-file outputs: `preprocessed.mlir`, `ttir-op-report.txt` (op counts from normalized IR), and `ops.mlir` (one func per unique op configuration, golden-style). Optional: per-pass IR dumps.
TTIR model op analysis (post-frontend-normalization)
Given a .mlir file (or a directory of .mlir files, e.g. a multi-graph model)
containing TTIR ops (from vLLM, torch-mlir, or tt-forge), normalize it the way the
compiler does before D2M, then inventory which TTIR ops (and shapes) appear. Do not
open TTIRToD2M.cpp, grep populateTTIRToD2MPatterns, or produce "D2M coverage"
unless the user explicitly asks for that comparison.
The input can be:
- A single
.mlirfile (e.g.model.mlir) - A directory of
.mlirfiles (e.g.vllm_opt/containinggraph1.mlir,graph2.mlir). Each file is processed independently with per-graph reports.
Step 1: Run the frontend TTIR normalization pipeline
These passes match createD2MFrontendPipeline in
lib/Dialect/D2M/Pipelines/D2MPipelines.cpp:
| # | Pass flag | Short name (for filenames) |
|---|---|---|
| 1 | --canonicalize | canonicalize |
| 2 | --ttir-predicate-type-alignment | predicate-type-alignment |
| 3 | --ttir-element-type-normalization | element-type-normalization |
| 4 | --ttir-to-ttir-decomposition | decomposition |
| 5 | --ttir-explicate-tms | explicate-tms |
| 6 | --ttir-erase-inverse-ops | erase-inverse-ops |
| 7 | --ttir-move-reshape-to-constant | move-reshape-to-constant |
| 8 | --ttir-fold-constant-reshape-broadcast | fold-constant-reshape-broadcast |
| 9 | --ttir-implicit-broadcast-fold | implicit-broadcast-fold |
Single-file mode
Create <basename>/ next to the input (basename = filename without .mlir):
<basename>/
preprocessed.mlir # IR after all passes above
ttir-op-report.txt # counts + sorted mnemonic list (see below)
ops.mlir # one func per unique TTIR op configurationsource env/activate
INPUT="<input.mlir>"
BASENAME="$(basename "$INPUT" .mlir)"
mkdir -p "$BASENAME"
ttmlir-opt \
--canonicalize \
--ttir-predicate-type-alignment \
--ttir-element-type-normalization \
--ttir-to-ttir-decomposition \
--ttir-explicate-tms \
--ttir-erase-inverse-ops \
--ttir-move-reshape-to-constant \
--ttir-fold-constant-reshape-broadcast \
--ttir-implicit-broadcast-fold \
-o "$BASENAME/preprocessed.mlir" \
"$INPUT"Directory mode (multi-graph models)
When the input is a directory like vllm_opt/ containing graph1.mlir,
graph2.mlir, etc., loop over each file and create a subdirectory per graph.
Each subdirectory uses clean names -- the folder provides the graph context:
vllm_opt/
graph1.mlir # original input
graph2.mlir
ttir-op-report.txt # combined report across all graphs
graph1/ # per-graph output folder
preprocessed.mlir
ttir-op-report.txt
ops.mlir
graph2/
preprocessed.mlir
ttir-op-report.txt
ops.mlirsource env/activate
INPUT_DIR="<dir>"
for f in "$INPUT_DIR"/*.mlir; do
STEM="$(basename "$f" .mlir)"
mkdir -p "$INPUT_DIR/$STEM"
ttmlir-opt \
--canonicalize \
--ttir-predicate-type-alignment \
--ttir-element-type-normalization \
--ttir-to-ttir-decomposition \
--ttir-explicate-tms \
--ttir-erase-inverse-ops \
--ttir-move-reshape-to-constant \
--ttir-fold-constant-reshape-broadcast \
--ttir-implicit-broadcast-fold \
-o "$INPUT_DIR/$STEM/preprocessed.mlir" \
"$f" || { echo "FAILED on $f"; continue; }
donettir-op-report.txt and ops.mlir
Do not hand-roll parsing. From the repo root (any Python 3.12+; no venv import deps). The script accepts multiple paths, so pass all preprocessed files in one command:
python tools/scripts/model_breakdown/ttir_model_op_inventory.py "$INPUT_DIR"/*/preprocessed.mlirThis writes ttir-op-report.txt and ops.mlir next to each preprocessed.mlir,
plus a combined ttir-op-report.txt at the common parent directory with per-file
summary and merged mnemonic counts.
Optional flags: --report PATH, --ops PATH (single-file only), -v.
The script reports: total "ttir.*" instances, per-mnemonic counts (with optional percentages),
distinct mnemonic count, and distinct op configurations (SSA-normalized op lines). ops.mlir
follows the same shape as test/python/golden/mlir_snippets/models/qwen3_4b/ops.mlir: one
func.func per unique configuration (<mnemonic>_<index>), args %arg0, ..., single op + return.
For multi-result ops such as ttir.sort and ttir.topk, the generated op must use MLIR
multi-result binding syntax (%0:2 = ...) and return projected results (return %0#0, %0#1 : ...). If you see operation defines 2 results but was provided 1 to bind, regenerate with
tools/scripts/model_breakdown/ttir_model_op_inventory.py instead of hand-editing every snippet.
Show full SKILL.md (152 more words)Show less
ttir.full and ttir.constant are excluded from ops.mlir unless their result is directly
returned by the module -- they almost always just produce values consumed by other ops, and are
already inlined as const producers inside those ops' test functions. The report still counts them.
It assumes one generic TTIR op per line (normal ttmlir-opt output). If needed, sanity-check
parse with ttmlir-opt on ops.mlir.
Optional: dump IR after each pass
Only if the user asks. Same pass loop as above; write
<basename>/<basename>.<short-name>.mlir for each stage. Final stage is the source for
ttir-op-report.txt and ops.mlir (same as *.implicit-broadcast-fold.mlir when you ran
all nine).
source env/activate
INPUT="<input.mlir>"
BASENAME="$(basename "$INPUT" .mlir)"
mkdir -p "$BASENAME"
PREV="$INPUT"
declare -a PASSES=(
"--canonicalize|canonicalize"
"--ttir-predicate-type-alignment|predicate-type-alignment"
"--ttir-element-type-normalization|element-type-normalization"
"--ttir-to-ttir-decomposition|decomposition"
"--ttir-explicate-tms|explicate-tms"
"--ttir-erase-inverse-ops|erase-inverse-ops"
"--ttir-move-reshape-to-constant|move-reshape-to-constant"
"--ttir-fold-constant-reshape-broadcast|fold-constant-reshape-broadcast"
"--ttir-implicit-broadcast-fold|implicit-broadcast-fold"
)
for entry in "${PASSES[@]}"; do
IFS='|' read -r FLAG SHORTNAME <<< "$entry"
OUT="$BASENAME/$BASENAME.$SHORTNAME.mlir"
ttmlir-opt $FLAG -o "$OUT" "$PREV" || { echo "FAILED at: $FLAG"; break; }
PREV="$OUT"
doneNOTE: If a pass fails, check include/ttmlir/Dialect/TTIR/Transforms/Passes.td for the
registered flag. Some setups need
--ttcore-register-device="system-desc-path=..." before other passes.
Step 2: Fill the report and ops.mlir
Run tools/scripts/model_breakdown/ttir_model_op_inventory.py on each preprocessed.mlir file
(single-file mode). See above.
Next: compile/run the snippets
To compile or execute the generated ops.mlir on device, see the
run-ops-mlir-snippets skill.
© tenstorrent, Apache-2.0. 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 .claude/skills/d2m-model-op-analysis of tenstorrent/tt-mlir.
Open the folder on GitHubat commit 78b7044
Compare with similar skills
Ttir Model Op Analysis 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 |
|---|---|---|---|---|---|---|
| Ttir Model Op Analysis this skilltenstorrent/tt-mlir | 314 | — | ~1.8k | Automated safety check: Pass | Apache-2.0 | |
| Gptqmodel Tokenizer NormalizationModelCloud/GPTQModel | 1.3k | — | ~1.1k | Automated safety check: Pass | Custom licence | |
| SQL Optimization Patternsynulihao/AgentSkillOS | 618 | 11 repos | ~3.3k | Automated safety check: Pass | None | |
| Datamodellmnimbalyst/nimbalyst | 1.9k | — | ~713 | Automated safety check: Pass | MIT | |
| Add Mpk Taskmirage-project/mirage | 2.5k | — | ~4.5k | Automated safety check: Pass | Apache-2.0 | |
| Sqlite Schema Designfastrepl/anarlog | 9.5k | — | ~1.9k | Automated safety check: Pass | MIT |
Similar skills
SQL Optimization Patterns
ynulihao/AgentSkillOS
Master SQL query optimization, indexing strategies, and EXPLAIN analysis to dramatically improve database performance and eliminate slow queries.
Datamodellm
nimbalyst/nimbalyst
Create visual data models for database schemas using Nimbalyst's DataModelLM editor.
Add Mpk Task
mirage-project/mirage
Step-by-step guide for adding a new task implementation to Mirage Persistent Kernel (MPK).
Sqlite Schema Design
fastrepl/anarlog
Design or review schemas for crates/cloudsync using SQLite Sync constraints, not generic SQLite advice.
DB Migrations
kurealnum/dotfiles
A skill your agent uses when generating or regenerating Drizzle migration files, changing database schema tables or columns, resolving migration sequence conflicts after rebase, reviewing migration…
More from tenstorrent/tt-mlir
All 9 skills in this repoAdd Op
tenstorrent/tt-mlir
How to add a new operation (op) to the tt-mlir compiler across all layers: TTIR/TTNN dialect definitions, StableHLO composite conversion, TTIR-to-TTNN conversion, EmitC/EmitPy conversions…
Add Ttir Builder Op
tenstorrent/tt-mlir
Add full builder API support (@tag, @parse, @split) for a TTIR op.
Run Ops Mlir Snippets
tenstorrent/tt-mlir
Compile and optionally execute every func.func in an ops.mlir-style snippet file (or every .mlir file in a directory) using runopsmlirsnippets.py.
Ttir Decomposition For Ttmetal
tenstorrent/tt-mlir
Add a new composite op decomposition pattern to the TTMetal pipeline.
Uplift Ttsim CI
tenstorrent/tt-mlir
Uplift the TTSim version used by tt-mlir CI and refresh WH/BH simulator skips.
Validate Tt Mlir Against Tt Xla
tenstorrent/tt-mlir
Validate a tt-mlir PR against tt-xla by creating a cherry-picked branch and triggering CI.
Related
Works with
Categories
Questions about Ttir Model Op Analysis
What does Ttir Model Op Analysis do?
Given a .mlir file (or a directory of .mlir files) with TTIR ops, run the same TTIR normalization passes as D2MFrontendPipeline before D2M, then produce per-file outputs: preprocessed.mlir…. Ttir Model Op Analysis is an agent skill from tenstorrent/tt-mlir.mlir (one func per unique op configuration, golden-style).
When should I use Ttir Model Op Analysis?
Ttir Model Op Analysis fits situations like: tasks that involve Database schema design.
How do I install Ttir Model Op Analysis in Claude Code?
Run `npx skills add tenstorrent/tt-mlir --skill ttir-model-op-analysis -a claude-code`. Or copy the skill folder (.claude/skills/d2m-model-op-analysis in tenstorrent/tt-mlir) into .claude/skills/ttir-model-op-analysis in your project. Claude Code loads it when a task matches its description.
How do I install Ttir Model Op Analysis in Codex?
Run `npx skills add tenstorrent/tt-mlir --skill ttir-model-op-analysis -a codex`. Or copy the skill folder (.claude/skills/d2m-model-op-analysis in tenstorrent/tt-mlir) into .agents/skills/ttir-model-op-analysis in your project. Codex loads it when a task matches its description.
Can I use Ttir Model Op Analysis 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 tenstorrent/tt-mlir --skill ttir-model-op-analysis -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/ttir-model-op-analysis, .gemini/skills/ttir-model-op-analysis, .github/skills/ttir-model-op-analysis and .opencode/skills/ttir-model-op-analysis in your project.
What does Ttir Model Op Analysis need to run?
Going by SKILL.md and its folder, Ttir Model Op Analysis needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Ttir Model Op Analysis 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 Ttir Model Op Analysis 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 Ttir Model Op Analysis use?
Ttir Model Op Analysis 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 Ttir Model Op Analysis use?
About 1.8k tokens (SKILL.md is roughly 7.3k 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 Ttir Model Op Analysis?
Skills that share tags, products or a category with Ttir Model Op Analysis: Gptqmodel Tokenizer Normalization (ModelCloud/GPTQModel, 1.3k stars), SQL Optimization Patterns (ynulihao/AgentSkillOS, 618 stars), Datamodellm (nimbalyst/nimbalyst, 1.9k stars) and Add Mpk Task (mirage-project/mirage, 2.5k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Ttir Model Op Analysis?
tenstorrent (a GitHub organization) maintains it in tenstorrent/tt-mlir, which has 314 GitHub stars. The repository holds 9 skills in this directory. The repository was last updated on October 10, 2026.
Source: tenstorrent/tt-mlir on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.