wave-execution-planner

Groups plan phases and tasks into dependency-ordered waves for parallel subagent execution via git worktrees. Builds a task dependency DAG, assigns wave numbers via topological sort, emits a living wave document that tracks status as work lands, and updates wave progress when tasks complete. Use when asked to: group tasks into waves, plan parallel execution, schedule worktrees, create a wave breakdown, wave planning, dependency grouping, update wave statuses, parallel subagents, which tasks can run in parallel.

Quality

88%

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

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.

Excellent structure, actionability, and progressive disclosure: the two-mode workflow is precise, validation gates are explicit, and bundle files are well-signaled and real. The one notable weakness is token efficiency — the unsafe-intermediate-state material is duplicated nearly verbatim across three sections.

Suggestions

Consolidate the safe-deploy-point guidance: state the principle once in Core Principles with a pointer to references/dependency-analysis.md, and remove the duplicated three-failure-mode listings from Mode A step 5 and the Anti-patterns entry.

Trim WHY lines that restate common knowledge (e.g., "early detection is always cheaper", "distributed status creates stale reads") to one short clause each.

Dimension	Reasoning	Score
Conciseness	The safe-deploy-point concept is explained three times — the Core Principles bullet defining the three failure patterns, Mode A step 5 restating the check, and the Anti-patterns entry re-listing all three failure modes with definitions — which is substantial repetition that could be consolidated into the existing dependency-analysis reference.	3 / 5
Actionability	Guidance is fully executable for a planning skill: a precise wave-assignment rule ("Wave 1 = tasks with no dependencies; Wave N = tasks whose all dependencies are in waves 1..N-1"), a concrete output path, runnable verification-gate commands, a status-transition diagram, and a worked recognition example with expected output.	5 / 5
Workflow Clarity	Both modes have numbered steps with explicit validation checkpoints — Mode A step 7 checks structural invariants, and Mode B requires the Verification checklist to pass before marking a wave DONE, with a Blocked recovery path and next-wave announcement.	5 / 5
Progressive Disclosure	The body is a lean overview and all four details (format, dependency analysis, status protocol, template) are pushed to one-level-deep reference files that exist on disk, each clearly signaled inline and summarized with descriptions in the References section.	5 / 5
	Total	18 / 20 Passed

Description

92%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 strong description: concrete third-person capability statements paired with an explicit, extensive trigger list. The only weakness is mild padding in the trigger enumeration, where redundant fragments could be trimmed in favor of a few missing natural phrasings.

Suggestions

Trim redundant trigger fragments (e.g., keep "group tasks into waves" and drop the near-duplicate "wave planning") and add missing natural phrasings such as "execution order" or "which tasks are independent".

Shorten the capability list slightly by merging "emits a living wave document that tracks status as work lands, and updates wave progress when tasks complete" into one clause, since both describe the same status-tracking mechanism.

Dimension	Reasoning	Score
Specificity	The description lists multiple concrete actions — "Builds a task dependency DAG, assigns wave numbers via topological sort, emits a living wave document that tracks status as work lands, and updates wave progress" — covering both modes of the skill comprehensively in third-person voice.	5 / 5
Completeness	It explicitly answers both "what" (five concrete capabilities) and "when" ("Use when asked to: group tasks into waves, plan parallel execution, ...") with concrete trigger phrases, matching the top anchor's example pattern.	5 / 5
Trigger Term Quality	Nine trigger phrases give good coverage with synonyms ("group tasks into waves", "create a wave breakdown", "wave planning"), but several entries are redundant fragments and a few natural user phrasings like "execution order" or "which tasks are independent" are missing.	4 / 5
Distinctiveness Conflict Risk	It occupies a clear niche — dependency-ordered wave planning for parallel subagent execution via git worktrees — with distinct trigger terms that are unlikely to fire for unrelated skills.	5 / 5
	Total	19 / 20 Passed

Validation

100%

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 — 16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository: pantheon-org/tekhne
Path: skills/project-mgmt/planning-toolkit/wave-execution-planner/SKILL.md
Commit: a1083f4

Reviewed: 3 hours 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.