Trellis Session Insight
mindfold-ai/Trellis
Reach into past AI conversation history through the trellis mem CLI.
AL debugging and diagnostics for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection.
Install Skill Debug
$ npx skills add javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install javiarmesto/ALDC-AL-Development-Collection skill-debug --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/javiarmesto/ALDC-AL-Development-Collection.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/skill-debug .claude/skills/skill-debug && 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 "skill-debug" agent skill from https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/skills/skill-debug into .claude/skills/skill-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-debug", 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/javiarmesto/ALDC-AL-Development-Collection/tree/main/skills/skill-debugType 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 javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install javiarmesto/ALDC-AL-Development-Collection skill-debug --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/skill-debug .agents/skills/skill-debug && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "skill-debug" agent skill from https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/skills/skill-debug into .agents/skills/skill-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-debug", 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 javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install javiarmesto/ALDC-AL-Development-Collection skill-debug --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/skill-debug .cursor/skills/skill-debug && 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 "skill-debug" agent skill from https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/skills/skill-debug into .cursor/skills/skill-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-debug", 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/javiarmesto/ALDC-AL-Development-Collection.git --path skills/skill-debug--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 javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install javiarmesto/ALDC-AL-Development-Collection skill-debug --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/skill-debug .gemini/skills/skill-debug && 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 "skill-debug" agent skill from https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/skills/skill-debug into .gemini/skills/skill-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-debug", 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 javiarmesto/ALDC-AL-Development-Collection skill-debugInstalls 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 javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/skill-debug .github/skills/skill-debug && 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 "skill-debug" agent skill from https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/skills/skill-debug into .github/skills/skill-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-debug", 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 javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install javiarmesto/ALDC-AL-Development-Collection skill-debug --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/javiarmesto/ALDC-AL-Development-Collection.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/skill-debug .opencode/skills/skill-debug && 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 "skill-debug" agent skill from https://github.com/javiarmesto/ALDC-AL-Development-Collection/tree/main/skills/skill-debug into .opencode/skills/skill-debug/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "skill-debug", 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
skill-debug- GitHub stars
- 109
- Token cost
- ~2.5k tokens
- SKILL.md length
- 714 words
- Files
- 1
- Skills in repo
- 14
- Repo updated
- First seen
- Licence
- MIT
At a glance
AL debugging and diagnostics for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection.
- Works in 4 steps: Context Gathering (MANDATORY before any… → Diagnose Root Cause → Document Diagnosis (MANDATORY) → …
- Performing snapshot debugging
- SKILL.md covers Purpose, When to Load, Core Patterns and Workflow, plus 2 more sections
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Skill Debug is an agent skill from javiarmesto/ALDC-AL-Development-Collection. AL debugging and diagnostics for Business Central. Use when performing snapshot debugging, CPU profiling, analyzing telemetry, or troubleshooting runtime issues.
Its SKILL.md is about 2.5k 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 Development, covering Debugging. The repository describes itself as: AL development toolkit for Business Central with specialist agents, skills and review workflows for Copilot, Claude Code and Codex. The licence is MIT.
When your agent uses it
- Performing snapshot debugging
- Analyzing telemetry
- Troubleshooting runtime issues
Example prompts
- “/skill-debug”
Workflow steps
4 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 161c3e3. 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 (its code samples are al and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
learn.microsoft.com
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
Skill Debug loads about 2.5k tokens when it runs. Until then it costs about 43 tokens; SKILL.md has 714 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 javiarmesto/ALDC-AL-Development-Collection at commit 161c3e3, republished under its MIT licence (© javiarmesto). 714 words, ~2,467 tokens.
Download SKILL.mdSave it as
.claude/skills/skill-debug/SKILL.md (or your agent's skills folder).- name
- skill-debug
- description
- AL debugging and diagnostics for Business Central. Use when performing snapshot debugging, CPU profiling, analyzing telemetry, or troubleshooting runtime issues.
Skill: AL Debugging & Diagnostics
Purpose
For BC29 AL0926 section-order errors or new isolation behavior, read the relevant sections of AL18 capability checks. Use actual compiler/runtime evidence and keep compilation distinct from execution.
Systematic diagnosis and root cause analysis for AL Business Central issues: runtime errors, logic bugs, intermittent failures, performance bottlenecks, and configuration problems.
When to Load
This skill should be loaded when:
- A runtime error, exception, or unexpected behavior is reported
- A logic bug needs root cause analysis (not just a symptom fix)
- An intermittent issue needs snapshot capture
- A performance bottleneck needs CPU profiling
- Configuration issues (auth, symbols, build, publishing) block development
- An event subscriber is not firing as expected
Core Patterns
Pattern 1: Choose Debugging Strategy
Select the right tool before starting:
| Issue Type | Strategy | Tool |
|---|---|---|
| Consistent runtime error | Standard debugger | al_debug |
| Already deployed code | Debug without publish | al_debug |
| Rapid dev cycle | Incremental publish | al_publish (incremental) |
| Intermittent / hard-to-reproduce | Snapshot debugging | al_snapshotdebugging |
| Slow performance | CPU profiling | VS Code command (not an agent tool) |
| Auth / symbols / build | Configuration troubleshoot | See Workflow Step 2b |
| Copilot AI feature | Agent session debug | launch.json with clientType: Agent |
Pattern 2: Data Flow Tracing
Scenario: "Value is wrong after posting"
1. Set breakpoint at final location (where value is wrong)
2. Work backwards to find where value is set
3. Use `usages` tool to find all assignments
4. Set breakpoints at each assignment point
5. Step through to find which execution path is taken
6. Inspect conditions and variable states at each pointPattern 3: Event Subscriber Not Firing
Scenario: "My event subscriber doesn't execute"
1. Verify subscriber signature exactly matches publisher (name, parameters, types)
2. Check SkipOnMissingLicense and SkipOnMissingPermission attributes
3. Confirm the extension containing the publisher is active and published
4. Set breakpoint inside subscriber body
5. Verify the publisher event is actually being raised (breakpoint in publisher)
6. Check if IsHandled = true is set before your subscriber runs
7. Inspect subscriber execution order (EventPriority)Pattern 4: Performance Bottleneck
// ❌ N+1 pattern — common cause of slow pages
repeat
Item.Get(SalesLine."No."); // DB call inside loop
SalesLine.Amount := Item.Price * SalesLine.Quantity;
until SalesLine.Next() = 0;
// ✅ Use SetLoadFields + single pass
SalesLine.SetLoadFields("No.", Quantity, Amount);
if SalesLine.FindSet() then
repeat
// ...
until SalesLine.Next() = 0;CPU profile analysis focus:
- Top time-consuming procedures (hotspots)
- Frequently called procedures in loops
- Expensive database operations
- FlowField CalcFormula complexity
Pattern 5: Snapshot Debugging for Intermittent Issues
⚠️ HUMAN GATE: Snapshots may capture sensitive runtime data.
Before initializing:
1. Confirm what data will be captured
2. Security review for sensitive information
3. Obtain explicit user approval
Commands (one tool — `al_snapshotdebugging` — covers initialize / finish / view):
al_snapshotdebugging (initialize) ← start capture session
[reproduce scenario 10-20 times]
al_snapshotdebugging (finish) ← end capture
al_snapshotdebugging (view) ← view and compare
Compare snapshots between success and failure cases:
- Variable values at failure point
- Timing differences
- Execution paths taken
- Data state variationsWorkflow
Step 1: Context Gathering (MANDATORY before any debugging)
Read existing plans context first:
.github/plans/memory.md ← project state and recent decisions
.github/plans/*-diagnosis.md ← previous debug sessions (similar issues)Gather issue information:
- What is the expected behavior vs actual behavior?
- When does it happen: always / sometimes / specific conditions?
- Exact error message and stack trace
- Recent code changes (potential regression source)
- User/permission set and environment where it occurs
Stop criterion: can reproduce the issue consistently (≥80% success rate).
Step 2a: Isolate the Problem (Runtime / Logic)
- Narrow down scope with
searchandusagestools - Identify suspect objects (tables, pages, codeunits, event subscribers)
- Attach debugger with selected strategy (Pattern 1)
- Set strategic breakpoints:
- Just before the error occurs
- At data modification points
- In event subscribers and validation triggers
- Inspect: variable values, record filters, call stack, parameter values
- Step execution: F10 (step over), F11 (step into), Shift+F11 (step out)
Step 2b: Configuration Troubleshooting
Authentication failures (401/403, cannot download symbols):
⚠️ HUMAN GATE: Clearing credentials disconnects active sessions.
Confirm impact and obtain approval before clearing the credentials cache
(a VS Code command, not an agent tool).
Then re-authenticate and verify launch.json authentication method.Missing symbols (unresolved references, red squiggles):
al_downloadsymbols ← first attempt
al_downloadsymbols (globalSourcesOnly) ← if no BC server connection is available
al_build ← verify compilationCheck app.json dependencies version alignment.
Build errors — common codes:
AL0896— Recursive FlowField: map dependency graph, break circular chainAL0185— Object ID conflict: check ID range inapp.json, no duplicatesAL0118— Field length mismatch: align extension field length with base table
Publishing failures: check environment connectivity, extension version increment, dependency resolution via al_packages.
Show full SKILL.md (285 more words)Show less
Step 3: Diagnose Root Cause
Identify the exact point of failure and — critically — WHY it occurs:
Common AL root causes by scenario:
| Symptom | Root Cause Candidates |
|---|---|
| Record Not Found | Wrong key values, filters blocking read, wrong company context, permission on read |
| FlowField wrong value | CalcFields not called, incorrect CalcFormula filters, circular dependency (AL0896) |
| OnValidate not firing | Direct assignment without Validate(), IsHandled = true in subscriber, disabled trigger |
| Custom event not firing | Signature mismatch, wrong ObjectType/ObjectId, publisher not raising event, compilation error in subscriber |
| Slow page | Missing SetLoadFields, N+1 loop, FlowField CalcFormula too complex, missing index/key |
| Intermittent failure | Race condition, timing dependency, data-state dependency, environment-specific |
Step 4: Document Diagnosis (MANDATORY)
Create .github/plans/<issue-kebab-case>-diagnosis.md before proposing any fix:
# Debug Session: <Issue Title>
**Date**: YYYY-MM-DD
**Severity**: Critical / High / Medium / Low
**Status**: Investigating → Diagnosed → Fixed → Verified
## Issue Summary
[Brief description]
## Symptoms
- Expected: [what should happen]
- Actual: [what happens — include exact error text]
## Reproduction Steps
1. [Step]
2. [Step]
**Reproducibility**: Always / Sometimes / Rare
## Root Cause
[Technical explanation with evidence — code snippet, line reference]
## Recommended Fix
[Specific solution. Short-term hotfix + long-term if needed]
## Testing Strategy
- Unit: [what to mock/test]
- Regression: [related functionality to verify]
## Next Steps
1. [Action]
2. [Action]File naming: sales-posting-error-diagnosis.md, slow-customer-list-diagnosis.md.
Step 5: Propose Fix & Handoff (MANDATORY HITL gate)
- Design fix addressing root cause (never symptoms only)
- Consider edge cases and side effects
- PAUSE — present diagnosis and proposed fix to user for approval
- After approval: handoff implementation to
al-developer(simple) or viaal-conductorTDD cycle (complex refactor) - After fix: run tests, re-profile if performance issue, verify regression scenarios
Clean up: remove debugging artifacts, breakpoints, and temporary logging from code.
References
Constraints
- This skill covers diagnosis and root cause analysis only — code changes are implemented by
al-developeror viaal-conductor - NEVER guess solutions without evidence from debugging tools
- NEVER skip Step 4 (diagnosis document) for non-trivial issues (>5 min investigation)
- NEVER proceed to fix without user approval (Step 5 HITL gate)
- NEVER leave debugging code, breakpoints, or temporary logging in production code
- Performance deep-dive (SetLoadFields, FlowField patterns, query optimization) → load
skill-performance.md - Event publisher/subscriber design patterns → load
skill-events.md - Permission set generation → load
skill-permissions.md
© javiarmesto, 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/skill-debug of javiarmesto/ALDC-AL-Development-Collection.
Open the folder on GitHubat commit 161c3e3
Compare with similar skills
Skill Debug 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 |
|---|---|---|---|---|---|---|
| Skill Debug this skilljaviarmesto/ALDC-AL-Development-Collection | 109 | — | ~2.5k | 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 | |
| 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 | |
| Systematic Debuggingultralisp/ultralisp | 258 | 51 repos | ~2.4k | Automated safety check: Pass | None |
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.
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
OpenLogi macOS Permissions Triage
AprilNEA/OpenLogi
Decides whether an OpenLogi device problem on macOS is a privacy-permission (TCC) problem, using agent log lines, and says which identity needs which grant.
More from javiarmesto/ALDC-AL-Development-Collection
All 14 skills in this repoSkill Agent Instructions
javiarmesto/ALDC-AL-Development-Collection
Generate, review, and optimize natural language instructions for Business Central agents (Designer or SDK).
Skill API
javiarmesto/ALDC-AL-Development-Collection
AL API development patterns for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection.
Skill Copilot
javiarmesto/ALDC-AL-Development-Collection
AL Copilot capability development for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection.
Skill Migrate
javiarmesto/ALDC-AL-Development-Collection
AL version migration for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection.
Skill Agent Task Patterns
javiarmesto/ALDC-AL-Development-Collection
Agent SDK task integration patterns for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection.
Skill Agent Toolkit
javiarmesto/ALDC-AL-Development-Collection
Build, configure, and integrate Business Central agents using the AI Development Toolkit and Agent SDK.
Related
Categories
Questions about Skill Debug
What does Skill Debug do?
AL debugging and diagnostics for Business Central. An agent skill from javiarmesto/ALDC-AL-Development-Collection. Skill Debug is an agent skill from javiarmesto/ALDC-AL-Development-Collection. AL debugging and diagnostics for Business Central.
When should I use Skill Debug?
Skill Debug fits situations like: performing snapshot debugging; analyzing telemetry; troubleshooting runtime issues.
How do I install Skill Debug in Claude Code?
Run `npx skills add javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a claude-code`. Or copy the skill folder (skills/skill-debug in javiarmesto/ALDC-AL-Development-Collection) into .claude/skills/skill-debug in your project. Claude Code loads it when a task matches its description.
How do I install Skill Debug in Codex?
Run `npx skills add javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a codex`. Or copy the skill folder (skills/skill-debug in javiarmesto/ALDC-AL-Development-Collection) into .agents/skills/skill-debug in your project. Codex loads it when a task matches its description.
Can I use Skill Debug 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 javiarmesto/ALDC-AL-Development-Collection --skill skill-debug -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/skill-debug, .gemini/skills/skill-debug, .github/skills/skill-debug and .opencode/skills/skill-debug in your project.
What does Skill Debug need to run?
SKILL.md names no scripts, command-line tools or credentials: Skill Debug is instructions for the agent only.
Does Skill Debug access the network?
SKILL.md names 1 domain. As links in the text: learn.microsoft.com. This is read from the text; nothing was executed.
Is Skill Debug 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 Skill Debug use?
Skill Debug 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 Skill Debug use?
About 2.5k tokens (SKILL.md is roughly 9.9k 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 Skill Debug?
Skills that share tags, products or a category with Skill Debug: Trellis Session Insight (mindfold-ai/Trellis, 15k stars), Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Aoti Debug (pytorch/pytorch, 104k stars) and Herdr Throwaway Reproduction (herdrdev/herdr, 43k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Skill Debug?
javiarmesto (a GitHub user) maintains it in javiarmesto/ALDC-AL-Development-Collection, which has 109 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 6, 2026.
Source: javiarmesto/ALDC-AL-Development-Collection on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.