CtrlK
BlogDocsLog inGet started
Tessl Logo

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.

20

Quality

7%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills/skills/autonomous-agents/SKILL.md

The canonical home for this skill is autonomous-agents in sickn33/agentic-awesome-skills

SKILL.md
Quality
Evals
Security

Quality

Content

11%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The body is a templated skeleton: persona framing, lists of well-known patterns defined in one line, empty anti-pattern headers, and a broken Sharp Edges table of placeholder rows. It provides no actionable guidance, no workflow, and no usable references.

Suggestions

Replace the one-line pattern descriptions with concrete, actionable guidance — example loop structures, guardrail configurations, or logging schemas the agent should actually apply.

Fill or remove the empty Anti-Patterns sections and repair the Sharp Edges table so each row names a real issue, severity, and concrete solution rather than repeating 'Issue' with dangling header links.

Add a sequenced workflow with validation checkpoints (e.g., constrain scope -> log -> validate against ground truth -> add autonomy only on success) since this skill concerns destructive/risky autonomous operations.

DimensionReasoningScore

Conciseness

The body is short but padded with concepts Claude already knows (one-line definitions of ReAct, Plan-Execute, Reflection) and stub/placeholder sections that add tokens without value, matching 'noticeably verbose; several unnecessary explanations or padded sections'.

2 / 5

Actionability

There is no concrete code, command, or executable guidance anywhere — only abstract descriptions like 'Alternating reasoning and action steps' and 'Separate planning phase from execution', matching the 'entirely vague or abstract; no concrete code' anchor.

1 / 5

Workflow Clarity

No multi-step process is sequenced and there are no validation checkpoints; anti-pattern sections are empty headers and the Sharp Edges table rows are broken placeholders ('Issue | critical | ## Reduce step count'), matching 'steps missing or incoherent; no sequence; no validation'.

1 / 5

Progressive Disclosure

Section headers exist but most sections are empty stubs and the Sharp Edges table is malformed; no bundle files exist and no references are signaled, so structure is minimal and content that should be filled is missing rather than appropriately split.

2 / 5

Total

6

/

20

Passed

Description

3%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description is a second-person persona narrative rather than a capability description: it conveys a mindset but states no concrete actions, no natural trigger terms, and no 'when to use' guidance. It would not help a user or Claude decide when to invoke this skill.

Suggestions

Rewrite the description in third person stating 2-4 concrete actions the skill performs (e.g., 'Designs constrained agent loops, adds guardrails and logging, validates reliability at scale').

Add an explicit 'Use when...' clause with natural trigger phrases users would actually say (e.g., 'Use when building autonomous agents, designing agent loops, or hardening agent reliability for production').

Remove the persona narrative and the statistics line; keep only capability and trigger information to maximize specificity and conciseness.

DimensionReasoningScore

Specificity

The description lists no concrete actions — it is pure persona framing ("You are an agent architect", "learned the hard lessons", "95% success rate per step means only 60% by step 10") with abstract language and no capabilities stated; the second-person voice also triggers the mandated specificity penalty, but it is already at the floor.

1 / 5

Completeness

It answers neither 'what does this do' (no actions described, only a persona) nor 'when should Claude use it' (no 'Use when...' clause or equivalent), so both what and when are missing/vague.

1 / 5

Trigger Term Quality

There are no natural keywords a user would say when needing this skill — only jargon ("autonomous AI", "agent architect") and no user-facing trigger phrases, matching the 'no natural keywords' anchor.

1 / 5

Distinctiveness Conflict Risk

It names a very broad domain (autonomous AI/agents) with high overlap risk against many agent-related skills, but it is not so generic as to conflict with virtually any skill, placing it just above the floor.

2 / 5

Total

5

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.