agent-readiness-report
Evaluate how well a codebase supports autonomous AI-assisted development. Analyzes repositories across five pillars (Agent Instructions, Feedback Loops, Workflows & Automation, Policy & Governance, Build & Dev Environment) covering 74 features. Use when users want to assess how agent-ready a repository is.
What this skill does
# Agent Readiness Report
Evaluate how well a repository supports autonomous AI-assisted development.
## What this does
Assess a codebase across five pillars that determine whether an AI agent can
work effectively in a repository. The output is a structured report identifying
what's present and what's missing.
## Five Pillars
| Pillar | Question | Features |
|--------|----------|----------|
| **Agent Instructions** | Does the agent know what to do? | 18 |
| **Feedback Loops** | Does the agent know if it's right? | 16 |
| **Workflows & Automation** | Does the process support agent work? | 15 |
| **Policy & Governance** | Does the agent know the rules? | 13 |
| **Build & Dev Environment** | Can the agent build and run the project? | 12 |
74 features total. See `references/criteria.md` for the full list with
descriptions and evidence examples.
## How to run
### Step 1: Run the scanner scripts
Five shell scripts gather filesystem signals — file existence, config patterns,
directory structures. They surface what's present so you don't have to run
dozens of `find` commands manually.
```bash
bash scripts/scan_agent_instructions.sh /path/to/repo
bash scripts/scan_feedback_loops.sh /path/to/repo
bash scripts/scan_workflows.sh /path/to/repo
bash scripts/scan_policy.sh /path/to/repo
bash scripts/scan_build_env.sh /path/to/repo
```
Or scan all five at once:
```bash
for s in scripts/scan_*.sh; do bash "$s" /path/to/repo; echo; done
```
**Important**: The scripts are helpers, not scorers. They find files and
patterns but do not evaluate quality. Many features require judgment that only
reading the actual files can provide — for example, whether a README includes
real build commands or just badges, whether inline documentation is systematic or
scattered, whether an AI usage policy has meaningful boundaries.
### Step 2: Evaluate each feature
Walk through `references/criteria.md` pillar by pillar. For each feature:
1. Check the scanner output for relevant signals
2. For features the scanner can't fully evaluate, inspect the files yourself
3. Mark each feature: **✓** (present), **✗** (missing), or **—** (not applicable)
Features that require judgment (not fully covered by scanners):
- Does the README actually contain build/run/test commands? (not just that it exists)
- Is inline documentation systematic across the public API?
- Are examples actually runnable?
- Does the contributing guide include code standards?
- Is there a meaningful AI usage policy?
- Is the architecture documentation current?
- Are tests documented well enough for an agent to run them?
### Step 3: Write the report
Structure the output as:
```
# Agent Readiness Report: {repo name}
## Summary
- Features present: X / 74
- Strongest pillar: {pillar}
- Weakest pillar: {pillar}
## Pillar 1 · Agent Instructions (X / 18)
✓ Agent instruction file — AGENTS.md at root
✓ AI IDE configuration — .cursor/rules/ with 3 rule files
✗ Multi-model support — only Cursor configured
...
## Pillar 2 · Feedback Loops (X / 16)
...
## Pillar 3 · Workflows & Automation (X / 15)
...
## Pillar 4 · Policy & Governance (X / 13)
...
## Pillar 5 · Build & Dev Environment (X / 12)
...
```
For each passing feature, briefly note what evidence you found.
For each failing feature, note what's missing.
## What makes these features useful
Every feature answers: *if this is missing, what goes wrong for the AI agent?*
Features like "agent instruction file" and "tool server configuration" exist
because agents need them. Features like "linter" and "CI pipeline" exist because
agents need fast, clear feedback on whether their changes are correct — not
because they're general best practices.
The criteria were derived from analysis of 123 real repositories across five
AI-readiness categories, then filtered for features that actually affect agent
effectiveness.
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.