CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

kanban-video-orchestrator

Plan and run multi-agent video production pipelines.

58

Quality

73%

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 ./optional-skills/creative/kanban-video-orchestrator/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

85%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.

A well-orchestrated overview: clear sequenced workflow with genuine validation gates and intervention feedback loops, with details correctly split into real, one-level-deep bundle files. Only minor tightening opportunities remain — slight intro/workflow redundancy and a couple of key invocations delegated entirely to references.

DimensionReasoningScore

Conciseness

The body is efficient and assumes competence — no generic-concept padding, every section carries skill-specific information (Hermes kanban mechanics, workspace rules, tool routing). The intro's numbered meta-pipeline list partially duplicates the Workflow section, and a few rule explanations could be trimmed one notch, keeping it just below the lean-everywhere anchor.

4 / 5

Actionability

Concrete, near-copy-paste guidance throughout: exact commands ("hermes kanban watch --tenant <project-tenant>"), concrete paths ("~/projects/video-pipeline/<slug>/"), exact parameter values ("workspace_kind=\"dir\" + workspace_path=\"<absolute project path>\""), and real generation scripts. Minor gap: the actual "bootstrap_pipeline.py" invocation and "hermes profile create" syntax live only in reference files rather than being shown inline.

4 / 5

Workflow Clarity

A clearly diagrammed 6-step sequence (DISCOVER → BRIEF → TEAM DESIGN → SETUP → EXECUTE → MONITOR) with an explicit user-confirmation gate on the brief ("Show the brief to the user for confirmation before designing the team"), pre-flight API-key verification, and a defined feedback loop (monitor → comment on failed task → re-run with parent → re-decompose), plus a Critical rules checklist — matching the top anchor.

5 / 5

Progressive Disclosure

A ~190-line overview that keeps orchestration logic inline and pushes all detail to well-signaled, bolded, one-level-deep references (intake.md, role-archetypes.md, tool-matrix.md, kanban-setup.md, monitoring.md, examples.md), all of which exist alongside the 3 templates and 2 scripts, and the annotated file map makes navigation trivial. Reference files link only laterally to siblings or to real scripts/templates, never chaining content another level deep.

5 / 5

Total

18

/

20

Passed

Description

53%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.

A concise, domain-clear description that names two concrete actions but stops there. Its main weakness is the total absence of any 'when to use' trigger guidance, which both caps completeness and thins natural keyword coverage. Third-person imperative voice is correct and no fluff is present.

Suggestions

Add an explicit trigger clause, e.g. "Use when the user wants a team-produced video (music video, narrative short, explainer, product teaser) rather than a one-shot render or conversion."

Include natural trigger synonyms users would actually say: "make/produce a video", "video pipeline", "animation pipeline", "orchestrate a video project".

Enumerate the core sub-actions (brief the request, design the agent team, generate the kanban setup, monitor execution) to lift specificity from two verbs to several concrete capabilities.

DimensionReasoningScore

Specificity

"Plan and run" names two concrete actions on a clear domain ("multi-agent video production pipelines"), but the description enumerates no further capabilities (scoping, team design, setup, monitoring), matching the "1-2 concrete actions, not comprehensive" anchor rather than the several-action anchor at 4.

3 / 5

Completeness

The 'what' is clear (plan and run multi-agent video production pipelines) but there is no 'Use when...' clause or equivalent trigger guidance anywhere in the description, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

"video" and "production" are natural terms a user might say, but this 8-word description misses common variations and synonyms users actually use ("make a video", "music video", "explainer video", "animation", "teaser"), fitting the "some relevant keywords but missing common variations" anchor.

3 / 5

Distinctiveness Conflict Risk

"multi-agent ... production pipelines" carves out a distinct niche unlikely to capture simple one-shot render requests; the only overlap risk is the bare word "video" competing with the many sibling renderer skills (ascii-video, manim-video, etc.), which is minor but real.

4 / 5

Total

13

/

20

Passed

Validation

81%

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

Validation — 13 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

metadata_version

'metadata.version' is missing

Warning

metadata_field

'metadata' should map string keys to string values

Warning

frontmatter_unknown_keys

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

Warning

Total

13

/

16

Passed

Repository

NousResearch/hermes-agent

Path

optional-skills/creative/kanban-video-orchestrator/SKILL.md

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.