Agent skill

complexity-gate

Estimate issue complexity before implementation to prevent timeouts. Uses cheap estimation to save expensive implementation tokens.

majiayu000github.com/majiayu000GitHub ↗
claude-coderead-onlyMIT
Install
npx skills add majiayu000/claude-skill-registry --skill complexity-gate-pcortes-swarm-attack --agent claude-code

Same command for any agent — swap --agent for codex, cursor, copilot.

Facts
Files in the skill folder: 2
SKILL.md size: 4 KB
Bundled scripts: none
Allowed tools: ReadGlob
Path: skills/analysis/complexity-gate-pcortes-swarm-attack/SKILL.md
Open the folder on GitHub →
Where it comes from
Stars: 534
Language: HTML

Weekly change comes from our own snapshots, not the repository page — it measures attention, not adoption.

From the SKILL.md

# Complexity Gate You estimate whether a GitHub issue is too complex for a single LLM implementation session. ## Task Given an issue's title, body, and acceptance criteria, estimate: 1. How many LLM turns the implementation would take 2. Whether the issue needs to be split into smaller pieces ## Complexity Guidelines | Complexity | Turns | Characteristics | |------------|-------|-----------------| | Simple | 5-8 | 1-3 criteria, single method, no edge cases | | Medium | 8-15 | 4-6 criteria, 2-4 methods, standard patterns | | Complex | 15-25 | 7-10 criteria, 5-7 methods, edge cases | | Too Large | 25+ | 10+ criteria, 8+ methods, multiple subsystems | ## Output Format Return ONLY JSON (no markdown, no explanation): ```json { "estimated_turns": 15, "complexity_score": 0.5, "needs_split": false, "split_suggestions": [], "confidence": 0.8, "reasoning": "Standard CRUD with 5 methods, well-defined interface" } ``` **Fields:** - `estimated_turns`: Number of LLM turns needed to implement (5-40) - `complexity_score`: Float from 0.0-1.0 indicating complexity - `needs_split`: Boolean indicating if issue should be split into smaller pieces - `split_suggestions`: List of actionable suggestions fo

What's inside
Steps it walks through
  1. Task
  2. Complexity Guidelines
  3. Output Format
  4. Red Flags (triggers auto-split)
  5. Turn Estimation Heuristics
  6. Formula
  7. Estimation Factors
  8. Tiered Estimation Strategy
  9. Examples
  10. Simple Issue (8 turns)
  11. Medium Issue (15 turns)
  12. Too Large (30+ turns - needs split)
Ships with 1 file
  • metadata.json
More from claude-skill-registry
All skills →
About this skill
What does the complexity-gate skill do?

Estimate issue complexity before implementation to prevent timeouts. Uses cheap estimation to save expensive implementation tokens.

How do I install it?

Run `npx skills add majiayu000/claude-skill-registry --skill complexity-gate-pcortes-swarm-attack --agent claude-code` — it drops the skill into your project so the agent can pick it up. Swap the --agent value for codex, cursor or copilot if you use one of those.

Where does this skill come from?

From majiayu000/claude-skill-registry, a repository with 534 stars. We read it straight from the repository tree rather than a submitted listing, so what you see here is what is actually published.

Is a popular skill a good skill?

Not necessarily. Stars measure attention, not adoption — a repository can trend for a week and be abandoned. That is why we show the weekly change from our own snapshots next to the total, instead of a single flattering number.

Keep going