CtrlK
BlogDocsLog inGet started
Tessl Logo

field-agent-deployment

Best practices for developing, testing, and deploying production-ready Field Agents including R&D workflows, version control, testing strategies, and release management

44

Quality

45%

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 ./field-agent-skills/deployment/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

31%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 content is a long, template-heavy monolith that explains familiar boilerplate and provides few executable steps, with its one deployment script left as a TODO placeholder. It needs to be split into reference files and refocused on concrete, verifiable deployment operations.

Suggestions

Move the README, technical-doc, release-notes, announcement, maintenance, and troubleshooting templates into separate files under references/ and link to them one level deep from SKILL.md.

Replace the TODO in deploy-agent.sh (and other placeholders) with concrete, runnable deployment commands, or explicitly justify the placeholder and point to the real tool.

Add explicit validation/rollback feedback loops to the deployment workflow (e.g., run smoke tests → if failures, rollback and re-validate) to lift workflow clarity above the destructive-operation cap.

Trim explanatory boilerplate (what a README contains, semantic versioning basics, troubleshooting table structure) since Claude already knows these.

DimensionReasoningScore

Conciseness

The ~420-line body is noticeably verbose, inlining large boilerplate templates (README, release notes, announcements, maintenance schedules) that re-state concepts Claude already knows and pad the context.

2 / 5

Actionability

Most guidance is fill-in templates and checklists rather than executable steps, and the one concrete script (deploy-agent.sh) leaves its core deployment step as a TODO placeholder.

2 / 5

Workflow Clarity

A sequenced Phase 1-3 publishing process with checklists exists, but as a production/deployment (destructive/batch) skill it lacks explicit validate-then-retry feedback loops, capping workflow_clarity at 3 per the rubric.

3 / 5

Progressive Disclosure

No bundle files exist yet ~300 lines of templates that clearly belong in separate reference files are inlined into SKILL.md, leaving only section headers as structure.

2 / 5

Total

9

/

20

Passed

Description

58%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 conveys a broad lifecycle scope with several concrete action areas, but it omits any explicit 'when to use' trigger guidance and relies on procedural keywords rather than natural user phrasing. It is reasonably distinct but would benefit from a trigger clause.

Suggestions

Add an explicit 'Use when...' clause naming concrete trigger scenarios (e.g., 'Use when deploying a Field Agent to production, preparing a release, or setting up a Field Agent dev workflow').

Incorporate natural user phrasing and synonyms (e.g., 'publish', 'release', 'ship to production', 'rollback') alongside the procedural terms.

Tighten the action list toward discrete operations (publish, migrate databases, run smoke tests, rollback) rather than broad process phases.

DimensionReasoningScore

Specificity

Names the Field Agent domain and several concrete lifecycle actions ('developing, testing, and deploying', 'R&D workflows', 'version control', 'testing strategies', 'release management'), with only minor coverage gaps.

4 / 5

Completeness

The 'what' is clear (full lifecycle best practices) but there is no 'Use when...' trigger clause, which per the rubric caps completeness at 3.

3 / 5

Trigger Term Quality

Relevant procedural keywords are present but it lacks the natural phrases a user would actually say and offers no synonyms or variations like 'deploy a Field Agent' or 'publish to production'.

3 / 5

Distinctiveness Conflict Risk

The Field Agent deployment/release niche is mostly distinct, with only minor overlap risk against general dev/deployment skills despite the somewhat generic 'Field Agents' label.

4 / 5

Total

14

/

20

Passed

Validation

100%

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

Validation — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
treasure-data/td-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.