create-context

Create baseline context from .context/session/in/ folder with manifest-driven organization (run once per project). Use when bootstrapping project context, setting up .context/session/ctx/ snapshot. Triggers include "create context", "bootstrap context", "setup context", "init context".

Quality

76%

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 ./skills/agentic-harness/create-context/SKILL.md

Quality

Content

68%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.

A well-structured, actionable skill body with strong bundle hygiene and a clearly sequenced workflow. Its main weakness is missing explicit validation in the step sequence for a batch/destructive operation, plus some body/reference duplication and undefined helpers.

Suggestions

Add an explicit validation step to the Steps sequence (e.g., step 4.5: run scripts/validate-manifest.sh after writing manifest.yaml and only proceed on pass) — the script exists in the bundle but is never sequenced in the workflow.

Deduplicate content between the body and references/reference.md — the token-threshold sizing table and security skip patterns appear in both; keep one-line summaries in the body and the full rules in the reference.

Replace or define the undefined `error` helper in the step-1 bash block with an executable pattern (e.g., `echo "..." >&2; exit 1`) and mention scripts/scan-in-folder.sh in the body since the body's step 2 reimplements its scan with a glob.

Dimension	Reasoning	Score
Conciseness	The body is dense and assumes Claude's competence (token-estimation formula, threshold tables, terse steps), but the sizing table and security skip patterns are duplicated between the body and references/reference.md, and the Anti-Patterns section pads some entries with lengthy Why prose, keeping it just below fully lean.	4 / 5
Actionability	Concrete executable guidance throughout (bash prerequisite checks, glob patterns, the priority/token threshold table, summary naming convention, find-based copy command), with minor gaps: the `error` helper in the step-1 bash block is undefined, and `Task(summarize-for-context)` depends on a sub-agent only documented in the reference file.	4 / 5
Workflow Clarity	Steps 1-7 are clearly sequenced, but this is a batch/destructive workflow (--force overwrite, bulk file copy) and the Steps sequence never explicitly runs scripts/validate-manifest.sh or any other validation checkpoint — validation is only implicit via the reference file and an anti-pattern note, so the batch-operation cap applies.	3 / 5
Progressive Disclosure	Good structure: SKILL.md is an overview, references/reference.md is a real, clearly signaled, one-level-deep file, and the two scripts exist in the bundle. Minor gaps: the scripts are surfaced only through reference.md rather than the body, and content duplicated between body and reference (sizing rules, security patterns) blurs the split.	4 / 5
	Total	15 / 20 Passed

Description

83%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: third-person, concrete, with explicit use-when guidance and enumerated trigger phrases. Its only weaknesses are minor — slightly incomplete action coverage and trigger space shared with sibling context skills.

Dimension	Reasoning	Score
Specificity	Names the domain and several concrete actions ("Create baseline context from .context/session/in/ folder with manifest-driven organization", "setting up .context/session/ctx/ snapshot") but omits capabilities like file prioritization and summarization, so coverage has minor gaps rather than being comprehensive.	4 / 5
Completeness	Clearly answers both what ("Create baseline context from .context/session/in/ folder with manifest-driven organization") and when ("Use when bootstrapping project context, setting up .context/session/ctx/ snapshot" plus concrete trigger phrases), matching the top anchor exactly.	5 / 5
Trigger Term Quality	Explicit natural trigger phrases ("create context", "bootstrap context", "setup context", "init context") give good keyword coverage, but a few natural variations users might say (e.g., "generate context", "context snapshot") are missing, falling just short of the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	The .context/session/ paths and (run once per project) qualifier carve out a clear niche, but triggers like "init context" and "setup context" sit in the same keyword family as the related save-context/load-context skills, creating minor overlap risk with closely related skills.	4 / 5
	Total	17 / 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
allowed_tools_field	'allowed-tools' contains unusual tool name(s)	Warning
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	14 / 16 Passed

Repository: pantheon-org/tekhne
Path: skills/agentic-harness/create-context/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.