CtrlK
BlogDocsLog inGet started
Tessl Logo

competition-file-parser-chain

Internal downstream skill for ctf-sandbox-orchestrator. CTF-sandbox workflow for file uploads, imports, previews, archive extraction, format conversion, parser invocation, and deserialization chains. Use when the user asks to inspect an upload or import path, trace archive extraction, preview or converter behavior, explain how a file reaches a parser or deserializer, or connect one uploaded artifact to the decisive backend effect. Use only after `$ctf-sandbox-orchestrator` has already established sandbox assumptions and routed here.

66

Quality

78%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

High

Do not use without reviewing

Fix and improve this skill with Tessl

tessl review fix ./CTF-Sandbox-Orchestrator/competition-file-parser-chain/SKILL.md
SKILL.md
Quality
Evals
Security

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 concise, well-structured instruction-only skill with good progressive disclosure and a single real reference file, but it lacks executable commands and explicit validation/verification checkpoints that this kind of file-processing inspection workflow would benefit from.

Suggestions

Add concrete executable examples (e.g., commands to dump multipart request shape, inspect magic bytes with `file`/xxd, list archive members) so the guidance moves from descriptive to copy-paste ready.

Insert an explicit validation/verification checkpoint into the workflow (e.g., 'Confirm the derived artifact you identified actually triggers the parser branch before reporting the decisive chain') to raise workflow clarity above the destructive/batch cap.

Format the reference pointer as a clearly labeled section (e.g., '## References\n- `references/file-parser-chain.md` — ingress checklist, parser checklist, evidence packaging') to sharpen navigation.

DimensionReasoningScore

Conciseness

Lean throughout: no padding, no explanation of concepts Claude already knows, every line is an instruction or checklist item; the language directive and routing guard each earn their place.

5 / 5

Actionability

The guidance is concrete in naming what to record (request shape, MIME guesses, temp paths, parser names) and what to distinguish, but it stops at descriptive checklists with no executable commands, code, or tooling examples for an instruction-only skill.

3 / 5

Workflow Clarity

The workflow is well-sequenced (ingress -> parser boundaries -> reduce to decisive chain) with a Quick Start list, but it involves file inspection/processing operations that mutate state yet lacks explicit validation or verification checkpoints, which caps clarity at 3 per the destructive/batch-operation guideline.

3 / 5

Progressive Disclosure

Clear overview in SKILL.md with a single, well-signaled one-level-deep reference (references/file-parser-chain.md, confirmed present) loaded for checklists; structure is good but the reference pointer is a plain prose line rather than a cleanly labeled section per file.

4 / 5

Total

15

/

20

Passed

Description

88%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, specific description that covers concrete capabilities, clear triggers, and explicit when-to-use gating with a well-defined downstream boundary. It would benefit from slightly less internal-jargon framing for end-user triggers.

Suggestions

Trim the internal-orchestrator framing ('$ctf-sandbox-orchestrator', 'downstream skill') slightly so the trigger phrasing reads as natural user speech rather than architecture description.

Add a couple of common synonyms or file-type examples (e.g., 'zip/tar archives', 'image/document conversion') to broaden trigger-term coverage.

DimensionReasoningScore

Specificity

Lists multiple concrete actions across the chain (file uploads, imports, previews, archive extraction, format conversion, parser invocation, deserialization chains), giving comprehensive coverage rather than a generic domain label.

5 / 5

Completeness

Explicitly answers 'what' (the upload-to-parser/deserializer workflow) and 'when' via a concrete 'Use when...' clause enumerating user intents, plus a scoping 'Use only after...' condition.

5 / 5

Trigger Term Quality

Strong natural trigger phrases ('inspect an upload or import path', 'trace archive extraction', 'preview or converter behavior', 'connect one uploaded artifact to the decisive backend effect') match what a user would say, though it leans on internal jargon ('$ctf-sandbox-orchestrator') rather than broad synonyms/extensions.

4 / 5

Distinctiveness Conflict Risk

The niche is clearly bounded to file-chain tracing within a downstream orchestrator relationship, with explicit 'Use only after' gating reducing conflict risk; minor overlap risk remains with adjacent worker/queue skills, which the description itself acknowledges.

4 / 5

Total

18

/

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
zhaoxuya520/reverse-skill
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.