budget-negotiator

An advanced skill for L3 autonomous loops. When the token budget nears exhaustion, the agent analyzes its ROI and autonomously drafts a negotiation request for a budget increase rather than silently failing.

Quality

70%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/budget-negotiator/SKILL.md

Quality

Content

78%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 lean, well-structured instruction-only skill with concrete file and field references, clear precedence rules, and an explicit escalation protocol. The main gap is the absence of a formal validation/feedback loop around the resume step.

Suggestions

Add an explicit validate-fix-retry loop for the Resume step, e.g., re-check loop-budget.md on the next run and re-escalate only if the cap was not raised.

Tighten or trim the 'Goal' section since it restates the Rules & Precedence content.

Provide a short justification-drafting template so the 'Draft Justification' step is fully executable rather than open-ended.

Dimension	Reasoning	Score
Conciseness	The body is efficient and assumes Claude's competence, with no padding explaining basic concepts, though the 'Goal' section restates the rules and the example block is somewhat long.	4 / 5
Actionability	It provides concrete guidance: specific files (loop-run-log.md, STATE.md, loop-budget.md), fields (actions_taken, outcome, tokens_estimate), the [BUDGET NEGOTIATION] tag, exact caps (+20% or +50k), and a copy-ready example, but the 'draft a concise business justification' step remains open-ended.	4 / 5
Workflow Clarity	The four-step protocol (Calculate ROI, Draft Justification, Escalate, Resume) is clearly sequenced with a verification checkpoint before resuming, but there is no explicit validate-fix-retry feedback loop.	4 / 5
Progressive Disclosure	At under 50 lines with no need for external reference bundles, the skill is well-organized into clear sections (Goal, Rules & Precedence, Negotiation Protocol) satisfying the simple-skill exception.	5 / 5
	Total	17 / 20 Passed

Description

62%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 reasonably clear and specific, covering both what the skill does and when it activates, with a distinct niche. It is weakened by jargon-heavy trigger language and a somewhat abstract when-condition that lacks concrete thresholds.

Suggestions

Add natural trigger phrases a user or loop would say (e.g., 'running out of tokens', 'request more budget') alongside the technical terms.

Make the when-condition more concrete by including the spend threshold (e.g., 'Use when token spend reaches 90% of the daily cap').

Soften jargon like 'L3 autonomous loops' and 'ROI' or pair them with plainer equivalents to broaden recognizability.

Dimension	Reasoning	Score
Specificity	The description names the domain (token budgets for autonomous loops) and two concrete actions ('analyzes its ROI' and 'autonomously drafts a negotiation request for a budget increase'), but the action set is not comprehensive enough for a 4.	3 / 5
Completeness	Both what (analyze ROI, draft a negotiation request) and when ('When the token budget nears exhaustion') are present, but the trigger condition could be more concrete with explicit thresholds.	4 / 5
Trigger Term Quality	It includes some relevant keywords ('token budget nears exhaustion', 'budget increase', 'negotiation request'), but leans heavily on technical jargon ('L3 autonomous loops', 'ROI') and omits common synonyms or natural phrasings a user would say.	3 / 5
Distinctiveness Conflict Risk	It occupies a clear niche (budget negotiation for autonomous loops) with distinct triggers, though there is minor overlap risk with the related loop-budget skill.	4 / 5
	Total	14 / 20 Passed

Validation

93%

Warnings & errors only

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

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
relative_links	Relative link issues: 1 suspicious	Warning

	Total	15 / 16 Passed

Repository: cobusgreyling/loop-engineering
Path: skills/budget-negotiator/SKILL.md
Commit: 0dc0f3f

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

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.