CtrlK
BlogDocsLog inGet started
Tessl Logo

long-horizon-prompting

This skill should be used when writing, enhancing, or evaluating the launch prompt for a long-running autonomous agent or a parallel multi-agent orchestration attacking a hard problem: pseudo-formal task briefs that define terms and an exact success predicate linguistically, enumerate non-counting outcomes, set persistence rules with explicit stop and return conditions and effort floors, manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping, and gate the return on adversarial audit. Route agent topology and coordination protocols to multi-agent-patterns, runtime control surfaces and loop governance to harness-engineering, evaluator and quality-gate construction to evaluation, judge design to advanced-evaluation, and compaction or memory mechanics to context-compression and memory-systems.

70

Quality

85%

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

SKILL.md
Quality
Evals
Security

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.

The content is well-structured with strong progressive disclosure, a clear validated workflow, and concrete actionable templates. Its chief weakness is conciseness: key rules are restated across the Core Concepts, Guidelines, and Gotchas sections, inflating the token budget without adding new information.

Suggestions

Consolidate the repeated rules that appear in Core Concepts, Guidelines, and Gotchas — keep one authoritative statement and cross-reference it, rather than restating 'pair every persistence instruction with a verification gate' three times.

Tighten the prose sections (e.g., 'Persistence Cuts Both Ways', 'The Verification Bottleneck') into bullet points so each rule earns its tokens.

Move the 'Generalizing Beyond Mathematics' transformation table into the task-brief-template reference, keeping only a one-line pointer inline, to further reduce body length.

DimensionReasoningScore

Conciseness

The body is substantive and expert-level rather than padding basics, but the same rules recur across Core Concepts, Guidelines, and Gotchas (persistence paired with verification, predicate-based return, blocked-route bookkeeping, rejecting status reports), and several prose sections could be tightened without losing meaning.

3 / 5

Actionability

Provides concrete, copy-paste-ready artifacts — an 8-step Brief-Writing Workflow, a brief skeleton template, a weak-to-strong transformation example, a generalization table, and a pre-launch evaluation checklist — with only minor gaps (placeholder fields in the skeleton are justified flexibility).

4 / 5

Workflow Clarity

The Brief-Writing Workflow is a clearly sequenced 8-step process culminating in an explicit red-team validation step ('Red-team the brief before launch... and patch every credible answer'), and the Pre-Launch Evaluation section supplies a yes/no checklist with feedback-loop guidance — matching the clear-sequence-with-validation-and-checklists anchor.

5 / 5

Progressive Disclosure

The body is an overview that offloads detailed material to one-level-deep, clearly signaled references — cdc-prompt-annotated.md, research-evidence.md, vendor-guidance.md, task-brief-template.md — all of which exist under ./references/ and are listed again with descriptions in the References section, giving easy navigation.

5 / 5

Total

17

/

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.

The description is specific, complete, and highly distinctive, explicitly answering both what and when while disambiguating from adjacent skills. Its main weakness is jargon-heavy trigger phrasing that underuses the natural synonyms a user might actually say.

Suggestions

Add plain-language trigger synonyms (e.g., 'agent prompt', 'long-running task', 'open-ended problem') alongside the technical terms to broaden natural keyword coverage.

Trim the long enumeration of brief internals (e.g., 'approach registry and blocked-route bookkeeping') in favor of one or two higher-level phrases, since trigger-term quality rewards natural phrasing over completeness of mechanism.

DimensionReasoningScore

Specificity

Lists multiple concrete actions — 'writing, enhancing, or evaluating the launch prompt', 'define terms and an exact success predicate', 'enumerate non-counting outcomes', 'set persistence rules', 'manage a diverse portfolio of parallel approaches with an approach registry and blocked-route bookkeeping', 'gate the return on adversarial audit' — giving comprehensive coverage of what the skill does.

5 / 5

Completeness

Explicitly answers both: 'when' via 'This skill should be used when writing, enhancing, or evaluating the launch prompt...' and 'what' via the enumerated brief components and routing clauses, with concrete trigger phrases.

5 / 5

Trigger Term Quality

Natural trigger phrases like 'launch prompt for a long-running autonomous agent', 'parallel multi-agent orchestration attacking a hard problem' are present and would be said by the target audience, but the body of the description leans on jargon ('pseudo-formal task briefs', 'blocked-route bookkeeping') and omits common synonyms.

4 / 5

Distinctiveness Conflict Risk

Carves a clear niche and explicitly routes adjacent work away — 'Route agent topology... to multi-agent-patterns, runtime control surfaces... to harness-engineering, evaluator... to evaluation, judge design... to advanced-evaluation, compaction... to context-compression and memory-systems' — minimizing conflict risk.

5 / 5

Total

19

/

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.

Validation16 / 16 Passed

Validation for skill structure

No warnings or errors.

Repository
muratcankoylan/Agent-Skills-for-Context-Engineering
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.