Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add huuanh20/awesome-ai-agent-skills --skill when-stuckgit clone --depth 1 https://github.com/huuanh20/awesome-ai-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/huuanh20/awesome-ai-agent-skills/when-stuck)<a href="https://agentmods.dev/skills/huuanh20/awesome-ai-agent-skills/when-stuck"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-agent-skills/when-stuck/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/huuanh20/awesome-ai-agent-skills/when-stuck"><img src="https://agentmods.dev/badge/skills/huuanh20/awesome-ai-agent-skills/when-stuck.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00022 | $0.00503 |
| Opus 5.5 | $0.00009 | $0.00201 |
| Sonnet 5.5 | $0.00004 | $0.00101 |
| Haiku 4.5 | $0.00002 | $0.00050 |
Grade A, and why
When Stuck - Problem-Solving Dispatch scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
When Stuck — Problem-Solving Dispatch
Overview
Different stuck-types need different techniques. This skill helps you quickly identify which problem-solving skill to use.
Core principle: Match stuck-symptom to technique.
Stuck-Type → Technique
| How You're Stuck | Use This Skill |
|---|---|
| Complexity spiraling — Same thing 5+ ways, growing special cases | simplification-cascades/SKILL.md |
| Need innovation — Conventional solutions inadequate, can't find fitting approach | collision-zone-thinking/SKILL.md |
| Recurring patterns — Same issue different places, reinventing wheels | meta-pattern-recognition/SKILL.md |
| Forced by assumptions — "Must be done this way", can't question premise | inversion-exercise/SKILL.md |
| Scale uncertainty — Will it work in production? Edge cases unclear? | scale-game/SKILL.md |
| Multiple independent problems — Can parallelize investigation | Use Agent tool with parallel subagents |
Process
- Identify stuck-type — What symptom matches above?
- Load that skill — Read the specific technique
- Apply technique — Follow its process
- If still stuck — Try different technique or combine
Combining Techniques
Some problems need multiple techniques:
- Simplification + Meta-pattern: Find pattern, then simplify all instances
- Collision + Inversion: Force metaphor, then invert its assumptions
- Scale + Simplification: Extremes reveal what to eliminate
Quick Dispatch
Same thing implemented 5+ ways? → simplification-cascades
Can't find fitting approach? → collision-zone-thinking
Same issue in 3+ different places? → meta-pattern-recognition
"This must be done this way"? → inversion-exercise
Will this survive production scale? → scale-game
Remember
- Match symptom to technique
- One technique at a time
- Combine if first doesn't work
- Document what you tried
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 58 lines · 22 tokens per session scan A 0b6bcc7ecafb
When Stuck - Problem-Solving Dispatch is a skill published in the GitHub repository huuanh20/awesome-ai-agent-skills (1 stars, last pushed 3mo ago), licensed MIT. It adds 22 tokens to every session and 503 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
loop
Work through the taskboard unattended for hours, pacing against the usage limits and filling the gap before a reset with CPU-only jobs. Use when asked to run all day, work unattended, or loop over tickets.
learn
Record a correction, decision, finding or failed attempt in the wiki. Use when the user corrects you, when a decision is made with a reason, when an experiment returns a verdict, or when you learn something the next session would otherwise re-derive.
wrap-up
Close out a task by folding what it taught into the wiki, updating the taskboard, and linting. Use at the end of a task, before clearing a session, or when asked to wrap up.
handoff
Write one self-contained goal that a fresh session can continue from. Use when context is running out, before clearing a session, when usage passes 95% on a long run, or when asked for a handoff.
init
Set up Dory in this repo by exploring it, creating wiki/ from the template, and connecting the usage statusline. Use when a project has no wiki/ yet, or when asked to set up Dory.
charles-proxy-extract
Extracts HTTP/HTTPS request and response data from Charles Proxy session files (.chlsj format), including URLs, methods, status codes, headers, request bodies, and response bodies. Use when analyzing captured network traffic from Charles Proxy debug sessions, inspecting API calls, debugging HTTP requests, or examining…