SkillAgentSearch skills...

autonomous-dev

A tool-agnostic behavioral specification for AI coding agents. Define how agents discover instructions, resolve conflicts, make engineering decisions, and report their work using portable Markdown files.

Install / Use

npx skills add iging/agent-spec

Installs into whichever agent you are using.

About this skill
🔧

.clinerules

Cline rules

Quality Score

65/100

Supported Platforms

Cline
Cursor
GitHub Copilot
Windsurf
Zed

Our assessment of autonomous-dev

autonomous-dev scores 65/100 on our quality scale, 1105th of 1,180 Content & Media skills we index.

Its .clinerules is 7.0 KB long, well organised into 15 sections with 1 code example: a thorough specification that gives an agent plenty to work with.

It has no GitHub stars yet, so there is no community track record; judge it on its content.

Substance
29/30
Structure
17/20
Description
15/15
Adoption
0/20
Freshness
5/15

Maintenance, license and trust

  • We could not determine when the repository was last updated.
  • Our last check on 2026-10-18 found the source still online.
  • No license is declared. By default that means all rights are reserved: you can read it, but reusing or redistributing it is not clearly permitted. Ask the author before building on it commercially.
  • Its trust signals score 68/100, with 3 cautions from licensing, adoption, age or documentation. These come from repository metadata, not a code audit — read the skill file before letting an agent act on it.

Safety scan

No issues found

Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful.

AI review by kimi-k2.7-code on 2026-09-23. Automated pattern scan on 2026-09-24. It catches known dangerous patterns, not every risk — read a skill before letting an agent act on it.

autonomous-dev compared with similar skills

All 4 of these similar skills score higher than autonomous-dev; compare them before choosing.

SkillScoreStarsUpdatedFormat
autonomous-dev (this skill)by iging650—.clinerules
Agent-Reachby Panniantong100109.0ktodayCLAUDE.md
headroomby headroomlabs-ai10078.9ktodayCLAUDE.md
Scraplingby D4Vinci10097.5ktodayMCP Server
crawl4aiby unclecode10086.9k1d agoMCP Server

Frequently asked questions

How do I install autonomous-dev?
Run npx skills add iging/agent-spec. The install tabs above show the steps for each supported agent.
Which AI agents does autonomous-dev work with?
It is written for Cline, Cursor, GitHub Copilot, Windsurf and Zed, as a .clinerules file. Other agents that read the same format can often use it too.
Is autonomous-dev safe to use?
Our scan of the whole file found no instruction hijacking, hidden characters, credential access, data exfiltration or destructive commands. An AI review of the same text found nothing harmful. It declares no license and scores 68/100 on trust signals. Skills are instructions an agent will follow, so read the file before installing it and do not approve commands you do not understand.
Is autonomous-dev still maintained?
We could not determine when the repository was last updated.

name: autonomous-dev description: >- Root router and lifecycle dispatcher for autonomous engineering skills. Executes phase classification and hands off work to specialized sub-skills. version: 1.0.0 verified-on: [claude-code, cursor, copilot, windsurf, kiro, cline, raw-api]

Autonomous Dev Router & Lifecycle Dispatcher

0. Identity

  • Role: Autonomous Software Engineering Lifecycle Dispatcher.
  • Authority: Normative root tier for skills/autonomous-dev/.
  • Must not define: Direct file edits or coding execution, routing logic hands off execution to specialized skills.
  • Normative base: core/decision-framework.md, shared/engineering/typescript-standards.md, shared/engineering/naming-conventions.md, shared/engineering/design-principles.md, shared/engineering/function-design.md, shared/engineering/module-organization.md, shared/writing/writing-rules.md, docs/anti-patterns.md.
  • Anti-pattern gate: Blocks AP-4, AP-26, AP-28, AP-44, and AP-45.

1. Intent (9 Dimensions)

| # | Dimension | Value | | --- | ---------------- | ------------------------------------------------------------------------------------- | | 1 | Task | Classify user requests into lifecycle phases and dispatch matching sub-skills. | | 2 | Target Tool | Any agent runtime: Claude Code, Cursor, Copilot, Windsurf, Kiro, Cline, or raw API. | | 3 | Output Format | Structured routing decision and target skill execution handoff. | | 4 | Constraints | No direct code edits within the router. Dispatch to sub-skill files. | | 5 | Input | User intent, prompt requests, feature ideas, bug reports, or pull requests. | | 6 | Context | Prevents premature code editing, context drift, and uncoordinated subagent execution. | | 7 | Audience | Autonomous agents and developers executing engineering tasks. | | 8 | Success Criteria | Exactly one primary target sub-skill path resolved and invoked deterministically. | | 9 | Examples | See Section 10. |

2. Trigger Matrix

| Trigger | Target Phase | Target Skill File Path | | --------------- | -------------------------------- | --------------------------------------------------------------- | | Design request | 01-ideation-and-design | 01-ideation-and-design/brainstorming.md | | Worktree setup | 02-isolation-and-workspace | 02-isolation-and-workspace/using-git-worktrees.md | | Branch cleanup | 02-isolation-and-workspace | 02-isolation-and-workspace/finishing-a-development-branch.md | | Task plan | 03-planning-and-decomposition | 03-planning-and-decomposition/writing-plans.md | | Subagent SDD | 04-execution-and-orchestration | 04-execution-and-orchestration/subagent-driven-development.md | | Batch plan | 04-execution-and-orchestration | 04-execution-and-orchestration/executing-plans.md | | Parallel agents | 04-execution-and-orchestration | 04-execution-and-orchestration/dispatching-parallel-agents.md | | TDD engine | 05-quality-and-testing | 05-quality-and-testing/test-driven-development.md | | Proof check | 05-quality-and-testing | 05-quality-and-testing/verification-before-completion.md | | Debugging | 06-debugging-and-investigation | 06-debugging-and-investigation/systematic-debugging.md | | Pre-review | 07-code-review-and-feedback | 07-code-review-and-feedback/requesting-code-review.md | | Review feedback | 07-code-review-and-feedback | 07-code-review-and-feedback/receiving-code-review.md | | Bootstrap | 08-meta-and-bootstrap | 08-meta-and-bootstrap/using-superpowers.md | | Meta authoring | 08-meta-and-bootstrap | 08-meta-and-bootstrap/writing-skills.md |

3. Execution Workflow

Step 1: Analyze Intent

  • Action: Read user prompt. Extract goal, scope, and technical target.
  • Input: User prompt text.
  • Stop Condition: Stop and ask user if intent is ambiguous.
  • Validation: Intent matches a row in the Trigger Matrix.

Step 2: Resolve Target Skill Path

  • Action: Select exact sub-skill path corresponding to the identified phase.
  • Input: Trigger Matrix table.
  • Stop Condition: Decline execution if no sub-skill matches.
  • Validation: Target file exists under skills/autonomous-dev/.

Step 3: Handoff Execution

  • Action: Invoke target sub-skill with contextual inputs.
  • Input: Resolved sub-skill path.
  • Stop Condition: Handoff transfers control to sub-skill.
  • Validation: Sub-skill executes internal workflow.

4. Output Specification

{
  "phase": "01-ideation-and-design",
  "target_skill": "skills/autonomous-dev/01-ideation-and-design/brainstorming.md",
  "reasoning": "Selected based on intent matching criteria."
}

5. Validation Gate

  • [ ] User intent mapped to exactly one lifecycle phase.
  • [ ] Target sub-skill file exists on disk.
  • [ ] Router executes no code or file edits directly.

6. Anti-Triggers and Calibration

  • Under-execution threshold: Failing to route leads to uncoordinated code edits.
  • Over-execution threshold: Routing single-line trivial fixes like typo corrections.
  • Calibration default: Route multi-step tasks, execute single-line edits directly.

7. Anti-Pattern Compliance

| Step | Prevents AP | Mechanism | | ---- | ---------------------------- | ----------------------------------------------- | | 1 | AP-1 (vague task) | Requires goal clarification before dispatching. | | 2 | AP-26 (no scope boundary) | Maps intent strictly to dedicated sub-skills. | | 3 | AP-4 (over-permissive agent) | Router cannot edit files directly. |

8. Versioning & Changelog

  • Version: 1.0.0
  • Changelog:
    • 1.0.0 : Initial router creation for skills/autonomous-dev/.

9. Portability Matrix

| Runtime | Status | Notes | | ----------- | -------- | ----------------------------- | | Claude Code | verified | Direct sub-skill invocation. | | Cursor | verified | .cursorrules route support. | | Copilot | verified | Custom instruction support. | | Windsurf | verified | Directive integration. | | Kiro | verified | Skill path linking. | | Cline | verified | System prompt directive. | | Raw API | verified | Model-agnostic router. |

10. Examples

Input: "Design a user authentication feature." Output: Phase 01-ideation-and-design, target 01-ideation-and-design/brainstorming.md.

Related Skills

View on GitHub
GitHub Stars0
CategoryContent
UpdatedNaNy ago
Forks0

Trust signals

68/100

From repository metadata: license, adoption, age and documentation. Not a code audit — see the Safety scan above for what the skill file itself contains.

2 medium1 low