Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
Working guide to the DKC1Recomp debugging/verification tool suite — builds, hosts, routes, detectors, regression gates, and the code atlas.
Install Dkc1 Tools
$ npx skills add elliotttate/DKC1Recomp --skill dkc1-tools -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install elliotttate/DKC1Recomp dkc1-tools --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/elliotttate/DKC1Recomp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/dkc1-tools .claude/skills/dkc1-tools && 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 "dkc1-tools" agent skill from https://github.com/elliotttate/DKC1Recomp/tree/main/.claude/skills/dkc1-tools into .claude/skills/dkc1-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dkc1-tools", 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/elliotttate/DKC1Recomp/tree/main/.claude/skills/dkc1-toolsType 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 elliotttate/DKC1Recomp --skill dkc1-tools -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install elliotttate/DKC1Recomp dkc1-tools --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliotttate/DKC1Recomp.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/dkc1-tools .agents/skills/dkc1-tools && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "dkc1-tools" agent skill from https://github.com/elliotttate/DKC1Recomp/tree/main/.claude/skills/dkc1-tools into .agents/skills/dkc1-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dkc1-tools", 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 elliotttate/DKC1Recomp --skill dkc1-tools -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install elliotttate/DKC1Recomp dkc1-tools --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliotttate/DKC1Recomp.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/dkc1-tools .cursor/skills/dkc1-tools && 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 "dkc1-tools" agent skill from https://github.com/elliotttate/DKC1Recomp/tree/main/.claude/skills/dkc1-tools into .cursor/skills/dkc1-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dkc1-tools", 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/elliotttate/DKC1Recomp.git --path .claude/skills/dkc1-tools--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 elliotttate/DKC1Recomp --skill dkc1-tools -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install elliotttate/DKC1Recomp dkc1-tools --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliotttate/DKC1Recomp.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/dkc1-tools .gemini/skills/dkc1-tools && 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 "dkc1-tools" agent skill from https://github.com/elliotttate/DKC1Recomp/tree/main/.claude/skills/dkc1-tools into .gemini/skills/dkc1-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dkc1-tools", 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 elliotttate/DKC1Recomp dkc1-toolsInstalls 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 elliotttate/DKC1Recomp --skill dkc1-tools -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/elliotttate/DKC1Recomp.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/dkc1-tools .github/skills/dkc1-tools && 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 "dkc1-tools" agent skill from https://github.com/elliotttate/DKC1Recomp/tree/main/.claude/skills/dkc1-tools into .github/skills/dkc1-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dkc1-tools", 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 elliotttate/DKC1Recomp --skill dkc1-tools -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install elliotttate/DKC1Recomp dkc1-tools --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/elliotttate/DKC1Recomp.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/dkc1-tools .opencode/skills/dkc1-tools && 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 "dkc1-tools" agent skill from https://github.com/elliotttate/DKC1Recomp/tree/main/.claude/skills/dkc1-tools into .opencode/skills/dkc1-tools/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "dkc1-tools", 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
dkc1-tools- GitHub stars
- 226
- Token cost
- ~1.8k tokens
- SKILL.md length
- 752 words
- Files
- 2
- Skills in repo
- 1
- Repo updated
- First seen
- Licence
- MIT
At a glance
Working guide to the DKC1Recomp debugging/verification tool suite — builds, hosts, routes, detectors, regression gates, and the code atlas.
- Works in 3 steps: Presentation/widescreen bug →… → Recomp-correctness bug (wrong dispatch,… → To understand intent, use the knowledge…
- Debugging widescreen/gameplay issues
- SKILL.md covers ⚠ Do not confuse the two…, Repo map, Where fixes go (never into… and Evidence discipline…, plus 1 more section
- Calls python
What it does
Dkc1 Tools is an agent skill from elliotttate/DKC1Recomp. Working guide to the DKC1Recomp debugging/verification tool suite — builds, hosts, routes, detectors, regression gates, and the code atlas. Use when debugging widescreen/gameplay issues, running evidence captures, or navigating the disassembly knowledge sources.
Its SKILL.md is about 1.8k tokens, which your agent loads only when the skill is triggered. The skill folder holds 1 other file (for example `TOOLS.md`).
It sits in Development, covering Debugging. The repository describes itself as: Static recompilation of Donkey Kong Country (SNES USA v1.0) with native widescreen presentation and deterministic debugging tools. The licence is MIT.
When your agent uses it
- Debugging widescreen/gameplay issues
- Running evidence captures
- Navigating the disassembly knowledge sources
Example prompts
- “/dkc1-tools”
Requirements
- Python 3
Workflow steps
3 steps, taken from the first numbered list in SKILL.md.
- Presentation/widescreen bug → ws_shadow.c, dkc1_game.c/
- Recomp-correctness bug (wrong dispatch, miscompile) →
- To understand intent, use the knowledge sources via
What it can do on your machine
Read from SKILL.md and the folder at commit 3eb9a10. 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
Dkc1 Tools loads about 1.8k tokens when it runs. Until then it costs about 68 tokens; SKILL.md has 752 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 elliotttate/DKC1Recomp at commit 3eb9a10, republished under its MIT licence (© elliotttate). 752 words, ~1,803 tokens.
Download SKILL.mdSave it as
.claude/skills/dkc1-tools/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- dkc1-tools
- description
- Working guide to the DKC1Recomp debugging/verification tool suite — builds, hosts, routes, detectors, regression gates, and the code atlas. Use when debugging widescreen/gameplay issues, running evidence captures, or navigating the disassembly knowledge sources.
DKC1Recomp tool suite
This repo is a static recompilation of Donkey Kong Country (SNES, USA
v1.0) with host-side widescreen presentation. Everything here follows
one contract: game logic stays byte-for-byte stock; widescreen is
presentation only (margins, camera bias, wider object visibility — never
changed simulation). The supported ROM is headerless USA v1.0,
sha256 fa8cacf5bbfc39ee6bbaa557adf89133d60d42f6cf9e1db30d5a36a469f74d15
(never commit ROMs, save states, captures, or generated game code).
⚠ Do not confuse the two widescreen efforts
There were TWO widescreen projects. Only this repo is current:
| This repo (current) | Legacy emulator hack (reference only) | |
|---|---|---|
| Approach | Host-side presentation over stock logic | ROM patched with asar (game code modified) |
| Location | C:\Users\ellio\Documents\GitHub\DKC1Recomp | in-repo consolidated copy: reference/legacy-widescreen/ (canonical for reading); originals at D:\Downloads\DKLR\DKC-Widescreen-358x224\, D:\Downloads\DKLR\DKC_Widescreen_358x224*.sfc (+398 variants, MSU1 builds), reference/disassembly/DKC1/Custom\Patches\Widescreen_358x224.asm, RomMap\ROM_Map_HACK_* |
| Use for | All new work | Prior-art reference: its worklog documents bug classes (OAM X-high wrap, exit-boundary coverage, section controllers) that inspired our detectors. Never copy its code or compare its patched-ROM behavior as "stock". |
If a file mentions 358x224, asar patching, or lives under
reference/legacy-widescreen/ or under D:\Downloads\DKLR\ outside the
disassembly's clean sources, it is the legacy effort. (Careful: the
RECOMP host renders 342x224 / 398x224 — a 398x224 mention alone does
not mean legacy; 358x224 always does.)
Repo map
runner/— host + adapters (dkc1_game.cpresentation glue,win32_host.cvisible debugger,headless_main.c, detectors)snesrecomp/— engine submodule (fork: elliotttate/snesrecomp;runner/src/snes/ws_shadow.cis the widescreen margin cache)recomp/*.cfg— recompiler configs incl. dispatch contracts (runtime-proven indirect-call target sets). Fixes for recompilation-correctness bugs go HERE, then regenerate.generated/— machine-emitted game C. Never hand-edit or commit.tools/— the analysis/verification suite (seeTOOLS.mdhere)recipes/*.dks— deterministic input routes;contracts/*.json— regression contracts;docs/KNOWN_ISSUES.json+docs/DASHBOARD.md- Build:
build_host_tools.bat(isolated tool-session build →build/dkc1_headless_tools.exe,dkc1_desktop_tools.exe,dkc1_layer_capture.exe),build_host.bat(primary),build_host_noadapt.bat(no-widescreen-adapter oracle). All embed build identity (git commit shown in window title / state sidecars).
Where fixes go (never into decompiled/generated code)
- Presentation/widescreen bug →
ws_shadow.c,dkc1_game.c/dkc1_video.cadapters, or the hosts. - Recomp-correctness bug (wrong dispatch, miscompile) →
recomp/*.cfg, regenerate. - To understand intent, use the knowledge sources via
python tools/atlas.py <addr|7Exxxx|name:term>— one query joins IDA's curated names/descriptions, disassembly+pseudocode listing, the live recompiled variant, dispatch contracts, WRAM labels, and known-issue mentions. Debug output (verdicts, click reports, trace PCs) pastes straight in.
Evidence discipline (non-negotiable)
- Detectors/taps are default-off (env-gated); arming one must never change emulation (A/B hash-identical).
- Watch transitions, not dumps; match actors by source record ($15FD), never by mutable pool slot.
- Routes are predicate-driven (
wait/pulseon WRAM), resolved to fixed input schedules before differential comparison. - A fix is verified only by 3× byte-identical replays including
end-of-run framebuffer/audio hashes (
tools/run_regression.pyenforces this plus ratcheted integrity budgets). - Event flags like
$1595are consumed same-frame — end-of-frame WRAM dumps cannot see them; watch durable effects (state, timers) instead. - WRAM semantics: see
tools/atlas.py wram:<addr>; key addresses are inTOOLS.md.
Show full SKILL.md (307 more words)Show less
Typical workflows
Widescreen bug of ANY kind: start at
docs/WIDESCREEN_PLAYBOOK.md — the symptom-first decision guide:
five entry points, the eight-rung localization ladder (pixel →
provenance → layers → policy → stock-vs-wide → reverse_watch →
atlas/irview/slice → oracle), the verdict/detector → owner table for
every invariant-monitor verdict, fix-ownership routing incl.
DKC1_REPLACE, the full verification ladder, and worked examples from
docs/KNOWN_ISSUES.json.
"Something looks wrong on screen" (visible host): click the pixel — the panel reports world coord, tile, provenance, last writer, OAM entries, nearest actor. F9 exports a repro bundle (rolling inputs + states + memory
- auto layer-isolation captures). With
DKC1_AUTO_EXPORT=1+DKC1_FLIGHT_RECORDER=1, any integrity detector exports automatically and appends a post-failure tail.
Reproduce + diagnose headlessly: run a recipe with taps armed, e.g.
DKC1_WIDESCREEN=1 DKC1_SCRIPT=recipes/route_jungle.dks DKC1_WS_TRACE=t.jsonl build\dkc1_headless_tools.exe <rom> 9000, then the matching analyzer
(analyze_ws_trace.py, lifecycle_by_source.py, analyze_retrodiction.py…).
Gate a fix: python tools/run_regression.py contracts/jungle-entry.json --exe build/dkc1_headless_tools.exe --rom <rom> --json-out build/regression/results.json, then python tools/make_dashboard.py.
Sweep everything: python tools/level_sweep.py --rom <rom>.
Pin a new bug: add it to docs/KNOWN_ISSUES.json with a repro; ratchet
its detector count in the contract budgets; tighten to 0 when fixed.
Full catalog of all 47 tools, every env var, route DSL, and debug keys:
TOOLS.md in this folder.
For battery/in-game saves, use verify_ingame_saves.py and
docs/INGAME_SAVES.md. Desktop hosts now persist SRAM: isolate their user
directory (SDL: DKC1_USER_DIR; legacy Win32: working directory). Headless
tests retain explicit SRAM input and never implicitly update a battery file.
For the native iPhone/iPad frontend, read docs/IOS.md. build_ios.sh builds
the app; tools/verify_ios_simulator.py compares three runs of the existing
headless runner inside the simulator app against three desktop runs.
DKC1_IOS_DIAGNOSTICS is a default-off build option. Mobile landscape chooses
a bounded native source width (418 on the connected phone) with fixed SNES
pixel proportions. Read docs/IOS.md for the limited validated scene scope.
The same default-off diagnostic build supports --verify-graphics, reusing
the native Metal output/cache oracle, plus paused upscale-preview captures.
See TOOLS.md for source-frame inputs, output hashes and UI probe limits.
© elliotttate, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in .claude/skills/dkc1-tools of elliotttate/DKC1Recomp.
- SKILL.md
- TOOLS.md
Open the folder on GitHubat commit 3eb9a10
Compare with similar skills
Dkc1 Tools 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 |
|---|---|---|---|---|---|---|
| Dkc1 Tools this skillelliotttate/DKC1Recomp | 226 | — | ~1.8k | Automated safety check: Pass | MIT | |
| Trellis Session Insightmindfold-ai/Trellis | 15k | 4 repos | ~1.7k | Automated safety check: Pass | AGPL-3.0 | |
| Native Data FetchingCherryHQ/cherry-studio-app | 4k | 6 repos | ~2.9k | Automated safety check: Notes | MIT | |
| Debugging Executionsn8n-io/n8n | 207k | — | ~2.6k | Automated safety check: Pass | Custom licence | |
| Aoti Debugpytorch/pytorch | 104k | 1 repos | ~1.7k | Automated safety check: Pass | Custom licence | |
| Herdr Throwaway Reproductionherdrdev/herdr | 43k | — | ~2.4k | Automated safety check: Pass | Apache-2.0 |
Similar skills
Native Data Fetching
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
- Official
Debugging Executions
n8n-io/n8n
Debug failed or wrong-output workflow executions using executions tools.
Aoti Debug
pytorch/pytorch
Debug AOTInductor (AOTI) errors and crashes. An agent skill from pytorch/pytorch.
Herdr Throwaway Reproduction
herdrdev/herdr
Runs a disposable, uniquely named Herdr session inside an existing one so runtime, pane, terminal or API bugs can be reproduced without touching the main session.
Systematic Debugging
ultralisp/ultralisp
A skill your agent uses when encountering any bug, test failure, or unexpected behavior, before proposing fixes
Related
Categories
Questions about Dkc1 Tools
What does Dkc1 Tools do?
Working guide to the DKC1Recomp debugging/verification tool suite — builds, hosts, routes, detectors, regression gates, and the code atlas. Dkc1 Tools is an agent skill from elliotttate/DKC1Recomp. Working guide to the DKC1Recomp debugging/verification tool suite — builds, hosts, routes, detectors, regression gates, and the code atlas.
When should I use Dkc1 Tools?
Dkc1 Tools fits situations like: debugging widescreen/gameplay issues; running evidence captures; navigating the disassembly knowledge sources.
How do I install Dkc1 Tools in Claude Code?
Run `npx skills add elliotttate/DKC1Recomp --skill dkc1-tools -a claude-code`. Or copy the skill folder (.claude/skills/dkc1-tools in elliotttate/DKC1Recomp) into .claude/skills/dkc1-tools in your project. Claude Code loads it when a task matches its description.
How do I install Dkc1 Tools in Codex?
Run `npx skills add elliotttate/DKC1Recomp --skill dkc1-tools -a codex`. Or copy the skill folder (.claude/skills/dkc1-tools in elliotttate/DKC1Recomp) into .agents/skills/dkc1-tools in your project. Codex loads it when a task matches its description.
Can I use Dkc1 Tools 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 elliotttate/DKC1Recomp --skill dkc1-tools -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/dkc1-tools, .gemini/skills/dkc1-tools, .github/skills/dkc1-tools and .opencode/skills/dkc1-tools in your project.
What does Dkc1 Tools need to run?
Going by SKILL.md and its folder, Dkc1 Tools needs the command-line tools its instructions call (python). Our summary lists: Python 3.
Does Dkc1 Tools 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 Dkc1 Tools 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 Dkc1 Tools use?
Dkc1 Tools 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 Dkc1 Tools use?
About 1.8k tokens (SKILL.md is roughly 7.2k 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 Dkc1 Tools?
Skills that share tags, products or a category with Dkc1 Tools: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Debugging Executions (n8n-io/n8n, 207k stars) and Aoti Debug (pytorch/pytorch, 104k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Dkc1 Tools?
elliotttate (a GitHub user) maintains it in elliotttate/DKC1Recomp, which has 226 GitHub stars. The repository was last updated on September 19, 2026.
Source: elliotttate/DKC1Recomp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.