autonomous-agents
You are an agent architect who has learned the hard lessons of autonomous AI. You've seen the gap between impressive demos and production disasters. You know that a 95% success rate per step means only 60% by step 10.
25
Quality
7%
Does it follow best practices?
Impact
Pending
No eval scenarios have been run
Passed
No known issues
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/autonomous-agents/SKILL.mdQuality
Discovery
0%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This description fails on all dimensions by presenting a persona/philosophy rather than describing concrete capabilities or usage triggers. It reads like flavor text rather than functional documentation. Claude would have no reliable way to determine when to select this skill over others.
Suggestions
Replace the persona narrative with concrete actions (e.g., 'Designs multi-step agent workflows, identifies failure points, calculates compound success rates').
Add an explicit 'Use when...' clause with natural trigger terms users would say (e.g., 'Use when building AI agents, designing autonomous workflows, or debugging multi-step AI systems').
Remove philosophical statements and focus on specific, distinguishable capabilities that differentiate this skill from general AI/coding skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | The description uses abstract, philosophical language ('agent architect', 'hard lessons', 'production disasters') without naming any concrete actions or capabilities. It describes a persona rather than what the skill does. | 1 / 3 |
Completeness | Neither 'what does this do' nor 'when should Claude use it' is answered. There is no 'Use when...' clause and no description of actual functionality—only a persona statement. | 1 / 3 |
Trigger Term Quality | Contains no natural keywords users would say when needing this skill. Terms like 'agent architect' and 'autonomous AI' are jargon, and '95% success rate' is a statistic, not a trigger term. | 1 / 3 |
Distinctiveness Conflict Risk | The description is so vague that it's unclear what domain this skill covers. 'Agent architect' and 'autonomous AI' could overlap with many AI-related skills without providing clear differentiation. | 1 / 3 |
Total | 4 / 12 Passed |
Implementation
14%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill content is severely incomplete and non-actionable. It names concepts (ReAct, Plan-Execute, Reflection) without explaining them, has a broken sharp edges table with placeholder text, and provides no executable code or concrete guidance. The philosophical framing takes up space that should contain actual implementation details.
Suggestions
Add concrete, executable code examples for each pattern (ReAct loop, Plan-Execute, Reflection) showing actual implementation
Fix the sharp edges table - replace 'Issue' placeholders with actual issues like 'Compounding errors', 'Cost explosion', 'Hallucinated tool calls'
Provide a clear step-by-step workflow for building a constrained agent, including validation checkpoints
Remove the capabilities keyword list and replace with actionable guidance or link to detailed pattern documentation
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | The content is relatively brief but includes some unnecessary philosophical framing ('You've seen the gap between impressive demos...') and the capabilities list is just keywords without actionable value. The sharp edges table is broken/incomplete. | 2 / 3 |
Actionability | The skill provides no concrete code, commands, or executable examples. Patterns like 'ReAct Agent Loop' and 'Plan-Execute Pattern' are named but not explained or demonstrated. The sharp edges table has placeholder 'Issue' text instead of actual issues. | 1 / 3 |
Workflow Clarity | No clear workflow or sequence is provided. The patterns section names approaches but doesn't explain steps. There are no validation checkpoints or feedback loops for implementing autonomous agents safely. | 1 / 3 |
Progressive Disclosure | The content is poorly organized with broken/incomplete sections. The sharp edges table is malformed with 'Issue' placeholders. References to related skills exist but no actual linked documentation or deeper content is provided. | 1 / 3 |
Total | 5 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
frontmatter_unknown_keys | Unknown frontmatter key(s) found; consider removing or moving to metadata | Warning |
Total | 10 / 11 Passed | |
- Repository
- sickn33/antigravity-awesome-skills
- Commit
9c177eb
- Reviewed
Table of Contents
Is this your skill?
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.