CtrlK
BlogDocsLog inGet started
Tessl Logo

acceptance-orchestrator

Use when a coding task should be driven end-to-end from issue intake through implementation, review, deployment, and acceptance verification with minimal human re-intervention.

65

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/agentic-awesome-skills-claude/skills/acceptance-orchestrator/SKILL.md

The canonical home for this skill is acceptance-orchestrator in boisenoise/skills-collections

SKILL.md
Quality
Evals
Security

Quality

Content

81%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 tightly organized orchestration state machine with explicit gates, validation checkpoints, stop/escalation conditions, and a concrete output contract. It is strong on workflow clarity and well-structured, with only minor redundancy and delegation-level (rather than code-level) actionability holding it back.

Suggestions

Remove the duplicated polling-window listing (state it once in the Workflow and reference it from Inputs, or vice versa) to tighten conciseness.

Add a brief inline snippet showing the expected output-contract format so the guidance is directly executable rather than only descriptive.

DimensionReasoningScore

Conciseness

The body is lean and well-structured with short bullet lists and no concept padding, but the polling windows ('3m -> 6m -> 10m') are stated twice — once in Inputs and again in the Workflow step — a minor redundancy that could be trimmed.

4 / 5

Actionability

Gives concrete, specific guidance — named sub-skills to invoke, fixed defaults (max rounds = 2, dev default), and a precise output-contract field list — though much of it is delegation to sub-skills rather than directly executable code or commands, leaving minor gaps.

4 / 5

Workflow Clarity

A clear numbered 6-step workflow mapped to an explicit state machine, with validation checkpoints (issue gate, completion gate requiring 'fresh evidence', verification-before-completion), feedback/escalation loops, and human gates for destructive and prod operations.

5 / 5

Progressive Disclosure

Well-organized into clear sections (Overview, When to Use, State Machine, Workflow, Stop Conditions, Human Gates, Output Contract) with no nested references, but it is a single self-contained document with no progressive disclosure to deeper material — acceptable here, though it does not demonstrate multi-level navigation.

4 / 5

Total

17

/

20

Passed

Description

76%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 clearly and explicitly states both what the skill does and when to use it, with a concrete end-to-end orchestration trigger. It is held back slightly by process-level rather than operation-level action specificity and limited natural trigger-term variation.

Suggestions

Add one or two natural user-facing trigger phrases (e.g., 'take an issue to done', 'ship a ticket end-to-end') to broaden trigger-term coverage.

Tighten the action list from lifecycle phases to one or two concrete operations to lift specificity toward comprehensive coverage.

DimensionReasoningScore

Specificity

Lists several concrete lifecycle phases — 'issue intake through implementation, review, deployment, and acceptance verification' — giving broad coverage of the orchestration scope, though they are process-level phases rather than granular operations, leaving minor gaps.

4 / 5

Completeness

Explicitly answers both what ('driven end-to-end from issue intake through ... acceptance verification') and when ('Use when a coding task should be driven end-to-end ... with minimal human re-intervention') with a concrete trigger phrase.

5 / 5

Trigger Term Quality

Contains relevant terms like 'coding task', 'implementation', 'review', 'deployment', and 'acceptance verification', but lacks the common natural variations or synonyms a user might actually say (e.g., 'ship a ticket', 'take an issue to done').

3 / 5

Distinctiveness Conflict Risk

The 'end-to-end ... acceptance verification with minimal human re-intervention' niche is mostly distinct, but the generic mention of implementation/review/deployment carries minor overlap risk with general coding-delivery skills.

4 / 5

Total

16

/

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.

Validation — 15 / 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
sickn33/agentic-awesome-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.