p2p
Binance P2P trading assistant for natural-language queries about P2P/C2C market ads, the user's own P2P order history, order detail & appeal tracking, and advertisement publish & management. Use when the user asks about P2P prices, searching/choosing ads, comparing payment methods, reviewing P2P order history, checking order detail/appeal status, querying complaints, publishing/updating/managing P2P advertisements, or viewing merchant profiles. Do NOT use for spot/futures prices, exchange trading, deposits/withdrawals, on-chain transfers, or anything unrelated to P2P/C2C.
84
77%
Does it follow best practices?
Impact
97%
1.67xAverage score across 3 eval scenarios
Advisory
Suggest reviewing before use
Optimize this skill with Tessl
npx tessl skill review --optimize ./skills/binance/p2p/SKILL.mdQuality
Discovery
100%Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.
This is a strong skill description that clearly defines its scope around Binance P2P/C2C trading operations. It excels in all dimensions by listing specific capabilities, providing rich trigger terms, explicitly stating both when to use and when not to use the skill, and carving out a distinct niche separate from other crypto trading skills.
| Dimension | Reasoning | Score |
|---|---|---|
Specificity | Lists multiple specific concrete actions: querying P2P/C2C market ads, order history, order detail & appeal tracking, advertisement publish & management. The description enumerates distinct capabilities rather than using vague language. | 3 / 3 |
Completeness | Clearly answers both 'what' (P2P trading assistant for market ads, order history, appeal tracking, ad management) and 'when' (explicit 'Use when...' clause with detailed trigger scenarios). Also includes a 'Do NOT use' clause which further clarifies boundaries. | 3 / 3 |
Trigger Term Quality | Excellent coverage of natural terms users would say: 'P2P prices', 'searching/choosing ads', 'comparing payment methods', 'P2P order history', 'order detail', 'appeal status', 'complaints', 'publishing/updating/managing P2P advertisements', 'merchant profiles', 'P2P/C2C'. These are terms users would naturally use. | 3 / 3 |
Distinctiveness Conflict Risk | Highly distinctive with clear niche (Binance P2P/C2C trading). The explicit 'Do NOT use' clause for spot/futures/deposits/withdrawals creates sharp boundaries that minimize conflict with other crypto-related skills. | 3 / 3 |
Total | 12 / 12 Passed |
Implementation
55%Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.
This skill is highly actionable with excellent workflow clarity — every operation has concrete endpoints, parameters, step-by-step flows, and validation/confirmation checkpoints. However, it is severely bloated: the monolithic ~700-line file includes exhaustive output format templates, repeated status mappings, bilingual trigger examples, and detailed confirmation dialogs that should be split into reference files or condensed. The progressive disclosure is poor despite referencing external files that don't exist in the bundle.
Suggestions
Split output format templates, status code mappings, and API reference tables into separate reference files (e.g., `references/output-formats.md`, `references/status-codes.md`) and link from SKILL.md with one-line descriptions.
Remove or drastically condense the trigger example lists (Chinese + English examples for every scene) — Claude can infer intent without 3-4 example phrases per trigger.
Consolidate the repeated confirmation protocol descriptions — define the write-op confirmation rule once and reference it, rather than restating the full format in Scenes 1.5, 1.7, 2.2, 2.3, and 2.4.
Provide the referenced bundle files (`references/authentication.md`, `references/agent-sapi-api.md`) or inline the critical signing details concisely, since the bundle is empty and these are referenced as essential.
| Dimension | Reasoning | Score |
|---|---|---|
Conciseness | This skill is extremely verbose at ~700+ lines. It includes massive amounts of output format templates, exhaustive status code mappings, trigger examples in multiple languages, and detailed confirmation dialogs that could be condensed significantly. Many sections repeat information (e.g., limitations stated multiple times, write-op confirmation rules restated). Claude doesn't need this level of template hand-holding for formatting output. | 1 / 3 |
Actionability | The skill provides concrete, executable code examples (Python, bash, curl), specific API endpoints with methods and parameters, exact URL patterns, complete signing guidance, and detailed step-by-step workflows for every operation. The evidence upload 3-step flow and ad publish workflow are fully actionable with real endpoint paths and parameter tables. | 3 / 3 |
Workflow Clarity | Multi-step processes are clearly sequenced with explicit validation checkpoints. The evidence upload flow has numbered steps with success/failure indicators. Write operations have mandatory confirmation protocols. The cancel-complaint flow has a strict warning → confirmation → execute sequence. Appeal handling branches by status code with clear next actions. Error recovery guidance is provided throughout. | 3 / 3 |
Progressive Disclosure | The entire skill is a monolithic wall of text with no content split into separate files. It references `references/authentication.md` and `references/agent-sapi-api.md` but no bundle files are provided. The output format templates, status code mappings, parameter reference tables, and Phase 3 content could all be split into separate reference files. Everything is inlined, making this extremely long for a SKILL.md overview. | 1 / 3 |
Total | 8 / 12 Passed |
Validation
90%Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.
Validation — 10 / 11 Passed
Validation for skill structure
| Criteria | Description | Result |
|---|---|---|
skill_md_line_count | SKILL.md is long (1083 lines); consider splitting into references/ and linking | Warning |
Total | 10 / 11 Passed | |
- Repository
- binance/binance-skills-hub
- Commit
68fcfa1
- 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.