CtrlK
BlogDocsLog inGet started
Tessl Logo

workflow

Workflow orchestration for complex coding tasks. Use for ANY non-trivial task (3+ steps or architectural decisions) to enforce planning, subagent strategy, self-improvement, verification, elegance, and autonomous bug fixing. Triggers: multi-step implementation, bug fixes, refactoring, architectural changes, or any task requiring structured execution.

60

Quality

69%

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 ./skills/workflow/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

67%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 well-structured, concise set of workflow directives with clear verification checkpoints, but much of the guidance is attitudinal rather than concretely actionable, and the two parallel numbering frameworks introduce mild redundancy.

Suggestions

Add a concrete worked example (e.g. a sample tasks/todo.md entry and a tasks/lessons.md pattern) to make the guidance executable and lift actionability above 3.

Consolidate the Workflow Orchestration (1-6) and Task Management (1-6) frameworks into a single sequenced workflow to remove redundancy and clarify the canonical process.

Trim motivational filler ('No Laziness', 'Senior developer standards', 'Would a staff engineer approve this?') to push conciseness toward 5.

DimensionReasoningScore

Conciseness

Mostly lean bullet directives that assume Claude's competence, with minor motivational padding ('No Laziness', 'Senior developer standards', 'Would a staff engineer approve this?', 'Ruthlessly iterate') that could be trimmed.

4 / 5

Actionability

Mixes concrete file references ('tasks/todo.md', 'tasks/lessons.md', plan mode) with abstract attitudinal directives ('use subagents liberally', 'throw more compute', 'demand elegance') and provides no concrete templates or worked examples.

3 / 5

Workflow Clarity

A clear numbered sequence (Task Management 1-6) with explicit checkpoints ('Verify Plan: check in', 'Never mark a task complete without proving it works', 'STOP and re-plan immediately'), though two overlapping numbering schemes cause minor confusion.

4 / 5

Progressive Disclosure

No bundle files exist and the body is self-contained with well-organized section headers; slightly over 50 lines with redundancy between the Workflow Orchestration and Task Management frameworks keeps it just below 5.

4 / 5

Total

15

/

20

Passed

Description

71%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 complete and trigger-rich, cleanly answering what and when, but its capabilities are framed as abstract process concepts and its 'ANY non-trivial task' scope is overly broad, raising conflict risk.

Suggestions

Replace abstract capability nouns (e.g. 'self-improvement', 'elegance') with one or two concrete actions to lift specificity above 3.

Narrow the trigger scope from 'ANY non-trivial task' to a more distinctive niche (e.g. multi-step implementation with subagent coordination) to reduce overlap with plan/code-review/verify skills.

Add natural synonyms or specific signal phrases (e.g. 'orchestrate subagents', 'plan-then-execute') to push trigger-term coverage toward 5.

DimensionReasoningScore

Specificity

Lists several named capabilities ('planning, subagent strategy, self-improvement, verification, elegance, and autonomous bug fixing') but these are abstract process concepts rather than concrete executable actions like 'extract text' or 'fill forms'.

3 / 5

Completeness

Clearly answers both 'what' (workflow orchestration enforcing planning/verification/etc.) and 'when' with explicit concrete trigger phrases ('Use for ANY non-trivial task (3+ steps or architectural decisions)' plus a dedicated Triggers clause).

5 / 5

Trigger Term Quality

'Triggers: multi-step implementation, bug fixes, refactoring, architectural changes, or any task requiring structured execution' provides good natural-phrase coverage users would actually say, though it lacks synonyms/variations.

4 / 5

Distinctiveness Conflict Risk

'Use for ANY non-trivial task (3+ steps or architectural decisions)' is deliberately maximalist and very broad, creating high overlap risk with plan, code-review, verify, and simplify skills.

2 / 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
brianlovin/agent-config
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.