CtrlK
BlogDocsLog inGet started
Tessl Logo

create-context-file

Creates a structured, date-stamped context file filed by typology (findings, plans, goals, evidence, guides, follow-ups, merge-requests, tickets, decisions, notes, research) with YAML frontmatter. Use when saving a finding, writing a plan, capturing a guide, recording a decision, logging a follow-up, filing a merge-request note, capturing work as progression evidence, plus ticket write-ups.

68

Quality

84%

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

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.

A well-structured skill body: executable quick commands with expected results, a checkpointed workflow with stop-if guards, and clean one-level-deep progressive disclosure into real bundle files. The only weakness is length in the anti-patterns section, where two entries explain downstream tooling behavior in depth that would sit better in a reference file.

Suggestions

Compress the two anti-patterns about empty list fields and `blocked-by` lifecycle semantics to a few lines each, moving the `context-ready.sh` fail-closed explanation into typologies.md or cli.md behind a load-when signal.

Trim the repeated "Expected result" prose in Quick Commands to a single line per command where the outcome is already evident from the command.

The `context-index` skill is referenced twice but never introduced; one clause stating the relationship (or a reference entry) would let readers skip it without losing the thread.

DimensionReasoningScore

Conciseness

The Quick Commands and Workflow sections are dense and earn their tokens, but the two anti-patterns on empty lists and `blocked-by` lifecycles spend roughly 50 lines explaining downstream `context-ready.sh` semantics that could be tightened or moved to a reference. Mostly efficient with some unnecessary explanation — anchor 3, above anchor 2 because there is no filler or explanation of concepts Claude already knows.

3 / 5

Actionability

Six copy-paste-ready bash commands cover the common cases (tags, related links, blocked-by, heredoc body, dry-run, new typology), each paired with an explicit "Expected result" line so success is checkable. Fully executable with specific examples — anchor 5.

5 / 5

Workflow Clarity

The four-step workflow carries an explicit checkpoint on every step: a duplicate check with expected output (step 2), "Verify: the printed path uses the expected typology plus date" (step 3), and "Stop if" guards on steps 1 and 4. Not anchor 4 because no checkpoint is merely implicit or missing; the file-creation operation is low-risk so the absence of an explicit fix-and-retry loop is not a gap.

5 / 5

Progressive Disclosure

The References section lists typologies.md, cli.md, and the frontmatter JSON schema, each with a "load when…" signal; all three files exist in the bundle and are one level deep with no chained references, and the bulk material (full CLI table, typology catalog, schema) correctly lives outside the body. Clear overview with well-signaled one-level-deep references — anchor 5.

5 / 5

Total

18

/

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 that explicitly states what the skill produces and when to use it, with a rich set of natural trigger phrases tied to a distinctive typology-based niche. The main gaps are the unbalanced trigger coverage (notes and research appear in the typology list but not the use-when clause) and reliance on a single verb for the capability statement.

Suggestions

Add natural trigger phrases for the `notes` and `research` typologies to the use-when clause so every listed typology has a matching trigger (e.g., "jotting a working note" or "starting a research log").

Mention the target directory (`.context/`) or the date-prefixed filename pattern in the description so users referencing the context directory by name trigger the skill.

Consider a second concrete verb (e.g., "links related artifacts via frontmatter") so the capability statement is not a single action.

DimensionReasoningScore

Specificity

"Creates a structured, date-stamped context file filed by typology (findings, plans, goals, evidence, guides, follow-ups, merge-requests, tickets, decisions, notes, research) with YAML frontmatter" names the domain and specifies the concrete artifact shape with the full typology enumeration. It centers on a single action rather than listing several distinct actions, so it sits just below the comprehensive anchor 5.

4 / 5

Completeness

It explicitly answers both what ("Creates a structured, date-stamped context file filed by typology … with YAML frontmatter") and when ("Use when saving a finding, writing a plan, … plus ticket write-ups") with concrete trigger phrases, matching anchor 5. Not anchor 4 because the when-clause is explicit and enumerates specific triggers rather than being merely adequate.

5 / 5

Trigger Term Quality

The use-when clause surfaces many natural phrasings ("saving a finding", "writing a plan", "capturing a guide", "recording a decision", "logging a follow-up", "filing a merge-request note"), but omits natural triggers for `notes` and `research` despite listing them as typologies, and includes no file or directory terms. Good coverage with a few natural terms missing — anchor 4, not anchor 5's comprehensive synonym/extension coverage.

4 / 5

Distinctiveness Conflict Risk

The typology enumeration carves a clear niche around persisted context files with minimal overlap risk, though generic requests like "create a plan" or "write this up" could pull in broader planning or documentation skills. Mostly distinct with minor overlap — anchor 4 rather than 5.

4 / 5

Total

17

/

20

Passed

Validation

87%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation14 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 deeper-than-1-level

Warning

referenced_paths_exist

Referenced path issues: 1 missing, 1 deeper-than-1-level

Warning

Total

14

/

16

Passed

Repository
pantheon-org/tekhne
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.