CtrlK
BlogDocsLog inGet started
Tessl Logo

crypto-bd-agent

Production-tested patterns for building AI agents that autonomously discover, > evaluate, and acquire token listings for cryptocurrency exchanges.

54

Quality

61%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

SecuritybySnyk

Low

Low-risk findings worth noting

Fix and improve this skill with Tessl

tessl review fix ./plugins/AI-Agents-Safe-Coding-Skills-claude/skills/crypto-bd-agent/SKILL.md

The canonical home for this skill is crypto-bd-agent in administrakt0r/AI-Agents-Safe-Coding-Skills

SKILL.md
Quality
Evals
Security

Quality

Content

60%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 skill is a well-structured, dense playbook with clear workflow gates and a distinct niche, but it carries time-sensitive version/date details that will date quickly and provides methodology without executable integration steps. Moving volatile specifics into a reference file and adding concrete API/command examples would raise the conciseness and actionability scores.

Suggestions

Move volatile specifics (model cascade versions, the Jan 29 2026 ERC-8004 date, per-call cost figures) into a separate 'reference/' file or a clearly dated section so the main body stays evergreen.

Add at least one concrete, copy-paste-ready integration example (e.g., a sample DexScreener/Helius API call or the x402 payment flow) to lift actionability beyond heuristics.

Add an explicit validate→fix→retry feedback loop for the outreach/batch steps (e.g., re-score after new source data, re-verify wallet forensics before re-queueing) to push workflow_clarity toward 5.

DimensionReasoningScore

Conciseness

The body is dense and table-driven without explaining basic concepts, but it embeds time-sensitive specifics (e.g., 'ERC-8004 went live... January 29, 2026', model cascade 'MiniMax M2.5 → Llama 70B → Haiku 4.5 → Opus 4.5', '$0.30/day') outside any deprecated/old-patterns section, which the guidelines say should penalize conciseness.

3 / 5

Actionability

It is an instruction-only skill and gives concrete heuristics (weighted scoring tables, score-action ranges, 5-step forensics, 10-stage pipeline), but it stops short of executable specifics — no API calls, no commands, and the actual integration detail is deferred to an external GitHub repo, leaving key implementation gaps.

3 / 5

Workflow Clarity

The architecture diagram plus the numbered 10-stage pipeline and score-gated actions (e.g., 70+ triggers forensics, human approval before send) give a clear sequence with most checkpoints present, though explicit validate→fix→retry feedback loops are not spelled out.

4 / 5

Progressive Disclosure

Well-organized into clearly numbered sections (1–6) with an architecture overview up top and a single external reference (the GitHub implementation); no nested references and no bundle files to mismanage, though some detailed tables could optionally live in reference files.

4 / 5

Total

14

/

20

Passed

Description

62%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 clearly conveys a distinct, well-scoped niche and names concrete agent actions, but it omits any explicit 'Use when...' trigger guidance, leaving the activation context unstated. The stray '>' character between 'discover,' and 'evaluate' is a minor formatting artifact. Adding a trigger clause and a few synonyms would lift the completeness and trigger-term dimensions.

Suggestions

Append an explicit 'Use when...' clause listing natural trigger phrases (e.g., 'Use when building a crypto/DeFi BD agent, token-listing pipeline, or multi-chain token scanning system').

Add common synonyms/extensions users would say — 'DeFi BD', 'token listing acquisition', 'crypto exchange onboarding' — to broaden trigger coverage.

Fix the stray '>' so the description reads 'discover, evaluate, and acquire' as clean prose.

DimensionReasoningScore

Specificity

Names the domain (crypto BD for exchanges) and several concrete actions — 'discover, evaluate, and acquire token listings' — comparable to the anchor listing several specific actions with minor coverage gaps.

4 / 5

Completeness

The 'what' is clear ('building AI agents that autonomously discover, evaluate, and acquire token listings') but the 'when' is entirely absent — no explicit trigger guidance, which per the judging guidelines caps completeness at 3.

3 / 5

Trigger Term Quality

Contains relevant natural terms ('token listings', 'cryptocurrency exchanges') but misses common variations/synonyms and lacks a 'Use when...' trigger phrase, so it sits at the middle anchor rather than above.

3 / 5

Distinctiveness Conflict Risk

Targets a very narrow niche (autonomous token-listing BD for crypto exchanges) with distinct triggers and minimal realistic overlap with other skills.

5 / 5

Total

15

/

20

Passed

Validation

93%

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

Validation15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

frontmatter_unknown_keys

Unknown frontmatter key(s) found; consider removing or moving to metadata

Warning

Total

15

/

16

Passed

Repository
administrakt0r/AI-Agents-Safe-Coding-Skills
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.