Tessl • The management layer for AI agent skills

SkillPublic

hyperplan

Adversarial multi-agent planning: a hostile team cross-critiques a plan before it is formalized. Use when planning needs maximum rigor or the user asks for a hyperplan / adversarial or cross-critique plan.

Quality

81%

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

77%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.

An exceptionally actionable orchestration skill with a rigorously sequenced 7-phase workflow and explicit validation checkpoints throughout. Its weaknesses are repetition (the planner-handoff mandate and injection-model notes are each stated many times) and a monolithic structure that inlines five member system prompts which belong in separate reference files.

Suggestions

State the Phase 6 planner-handoff contract once (in Phase 6 itself) and cut the restatements in the workflow intro, Phase 5, the anti-patterns table, and the Lead notes; a single bolded 'MANDATORY' plus one anti-pattern row preserves the emphasis at a fraction of the tokens.

Move the five member system prompts and the category characteristics table into references/member-prompts.md, keeping one-line role/attack-vector summaries in SKILL.md and substituting the prompts by reference in the team_create spec.

Explain the injection-driven delivery model once (in 'HOW THIS MAPS TO omo-senpi') and reduce the later repeats to one-line reminders.

Dimension	Reasoning	Score
Conciseness	The tool specs, message templates, and member prompts earn their tokens, but the planner-handoff contract is restated at least five times ('The handoff is the contract', 'MANDATORY planner handoff', anti-patterns table rows, Lead notes) and injection-driven delivery is re-explained three times. Mostly efficient, but clearly could be tightened — anchor 3, not 4, because the repetition is substantial rather than minor.	3 / 5
Actionability	Fully executable: exact team_create/task_send/task call signatures with arguments, verbatim round-task message templates, complete copy-paste-ready member system prompts, and a concrete fallback for an unresolvable 'deep-low' category. Anchor 5.	5 / 5
Workflow Clarity	Seven clearly sequenced phases with explicit checkpoints ('Collect every member's ... reply ... before continuing'), error-recovery paths (nudge stalled members, roster fallback, team_delete retry guidance), and a mandatory cleanup phase. Matches the anchor-5 pattern of sequence plus validation plus feedback loops.	5 / 5
Progressive Disclosure	No bundle files exist; the five full member system prompts (~140 lines) and the category characteristics table clearly belong in a references/ file but are inlined in a 455-line monolith. Section headers are clear, so above anchor 2, but content that should be separate is inline — anchor 3.	3 / 5
	Total	16 / 20 Passed

Description

78%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 with an explicit 'Use when' trigger clause and concrete trigger phrases, clearly distinguishing the skill's adversarial niche. Its main gap is specificity — it summarizes the mechanism in one clause rather than enumerating what the skill actually does.

Suggestions

Add one or two concrete mechanism details to the 'what' clause, e.g. '5 hostile members cross-critique findings over 3 rounds, then a dedicated planner formalizes the survivors into an executable plan'.

Add natural trigger synonyms users might say, such as 'red-team my plan' or 'critique this plan before committing', to broaden trigger coverage.

Tighten 'planning needs maximum rigor' to a more distinctive condition (e.g. 'high-stakes or irreversible work') to reduce overlap with ordinary planning requests.

Dimension	Reasoning	Score
Specificity	Names the domain and 1-2 concrete actions ('a hostile team cross-critiques a plan before it is formalized') but does not enumerate the actual mechanics (5 members, 3 rounds, distillation, planner handoff). Not 4 because it stops short of listing several specific actions.	3 / 5
Completeness	Explicitly answers both: what ('a hostile team cross-critiques a plan before it is formalized') and when ('Use when planning needs maximum rigor or the user asks for a hyperplan / adversarial or cross-critique plan') with concrete trigger phrases. Matches the anchor-5 example structure.	5 / 5
Trigger Term Quality	Good natural-term coverage: 'planning needs maximum rigor', 'hyperplan', 'adversarial ... plan', 'cross-critique plan'. Not 5 because common synonyms like 'red-team my plan' or 'critique this plan' are missing.	4 / 5
Distinctiveness Conflict Risk	'Adversarial multi-agent planning' and 'hyperplan' carve a clear niche with distinct triggers, but 'planning needs maximum rigor' is broad enough to overlap generic planning/request-planning skills. Minor overlap risk only.	4 / 5
	Total	16 / 20 Passed

Validation

87%

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 — 14 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_version	'metadata.version' is missing	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: code-yeongyu/oh-my-openagent
Path: packages/omo-senpi/skills/hyperplan/SKILL.md
Revision: 687f5af

Reviewed: 3 days ago

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.

hyperplan

Table of Contents

Is this your skill?