context-surfing

Monitors context window health throughout a session and rides peak context quality for maximum output fidelity. Activates automatically after plan-interview and intent-framed-agent. Stays active through execution and hands off cleanly to simplify-and-harden and self-improvement when the wave completes naturally or exits via handoff. Use this skill whenever a multi-step agent task is underway and session continuity or context drift is a concern. Especially important for long-running tasks, complex refactors, or any work where degraded context would silently corrupt the output. Trigger even if the user doesn't say "context surfing" — if an agent task is running across multiple steps with intent and a plan already established, this skill is live.

Quality

71%

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

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/context-surfing/SKILL.md

Quality

Content

63%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 thorough, well-structured behavioral skill with concrete commands, templates, and clearly sequenced protocols. It is held back by pervasive metaphorical padding and a monolithic structure that inlines content which would benefit from separate reference files.

Suggestions

Trim the ocean-wave metaphor (Mental Model and Principles sections) to one short paragraph; the operational protocols already convey the behavior without the extended analogy.

Move the full handoff-file markdown template and the hook JSON config into separate reference files under references/, keeping only a short pointer inline in SKILL.md.

Either bundle the referenced scripts/handoff-checker.sh or replace the hook example with a self-contained inline command so no referenced file is missing.

Dimension	Reasoning	Score
Conciseness	The body is mostly operational but the extended ocean-wave metaphor (Mental Model, Principles, repeated 'wave'/'shoulder'/'close-out' phrasing) adds padding that could be tightened without losing clarity.	3 / 5
Actionability	Provides concrete executable elements — bash commands (`entire status`, `ls .context-surfing/handoff-*.md`), a JSON hook config, and a complete copy-ready handoff file template — with only minor gaps in coverage.	4 / 5
Workflow Clarity	Exit Protocol and Recovery Protocol are clearly sequenced with explicit checkpoints and a reconcile feedback loop, and drift signals are presented as checklists; held back slightly because the 'validation' is self-monitoring rather than a hard verifiable gate.	4 / 5
Progressive Disclosure	Well-organized into labeled sections, but at ~365 lines it is monolithic — the handoff template and hook configs are inlined rather than split into reference files, and the referenced `scripts/handoff-checker.sh` is not present in the bundle.	3 / 5
	Total	14 / 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.

The description is well-constructed: third-person voice, explicit what-and-when trigger guidance, and clear positioning within a skill pipeline. Its main weakness is reliance on metaphorical language ('rides peak context quality') that blurs the concreteness of its stated capabilities.

Dimension	Reasoning	Score
Specificity	Names the domain ('context window health', 'peak context quality') and several actions (monitors, activates, hands off), but the actions are abstract/metaphorical rather than concrete technical operations, falling short of comprehensive coverage.	3 / 5
Completeness	Explicitly answers both 'what' (monitors context window health, rides peak context quality, hands off to downstream skills) and 'when' ('Use this skill whenever a multi-step agent task is underway and session continuity or context drift is a concern') with concrete trigger phrases.	5 / 5
Trigger Term Quality	Includes natural terms users would say ('multi-step agent task', 'session continuity', 'context drift', 'long-running tasks', 'complex refactors') with good coverage, though a few common phrasings are absent.	4 / 5
Distinctiveness Conflict Risk	Occupies a clear niche (context-quality drift during execution) and explicitly distinguishes itself from sibling skills like intent-framed-agent, with only minor overlap risk among the closely-related pipeline skills.	4 / 5
	Total	16 / 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: pskoett/pskoett-ai-skills
Path: .agents/skills/context-surfing/SKILL.md
Commit: 8a71d70

Reviewed: 6 days 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.