A guided workflow for creating a new coding-agent skill, a reusable set of instructions for a specific development task.

Use it to search current knowledge, answer targeted setup questions, and generate a compliant skill folder with its instructions, references, and templates.

It checks whether an existing skill already covers the topic, reducing duplicate work and inconsistent skill structures.

new-skill — Command for Claude Code by BanibrataChatterjee

Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo

git clone --depth 1 https://github.com/BanibrataChatterjee/AwesomeSalesforceSkills

agentmods

npx agentmods add commands/banibratachatterjee/awesomesalesforceskills/new-skill

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/new-skill/github.svg)](https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/new-skill)

Your own site

<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/new-skill"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/new-skill/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/commands/banibratachatterjee/awesomesalesforceskills/new-skill"><img src="https://agentmods.dev/badge/commands/banibratachatterjee/awesomesalesforceskills/new-skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 729 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00000	$0.00729
Opus 5.5	$0.00000	$0.00292
Sonnet 5.5	$0.00000	$0.00146
Haiku 4.5	$0.00000	$0.00073

Measured 2mo ago against content hash ca458c205617, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

new-skill scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

commands/new-skill.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/new-skill — New Skill Workflow

Triggers the skill-builder agent.

Usage

/new-skill

The agent checks local coverage first, asks targeted questions, then uses new_skill.py to scaffold a compliant package. Content is filled into the scaffold — the structure is never written from scratch.

What Happens

Step 1 — Coverage Check (do not skip)

python3 scripts/search_knowledge.py "<topic>" --domain <domain>

If has_coverage: true is returned, review the existing skill before creating a new one. Extend or differentiate — do not duplicate.

Step 2 — Scaffold

python3 scripts/new_skill.py <domain> <skill-name>

This creates the full directory structure:

skills/<domain>/<skill-name>/
├── SKILL.md                         ← pre-filled with TODO markers (includes Recommended Workflow section)
├── references/
│   ├── examples.md                  ← pre-filled with TODO markers
│   ├── gotchas.md                   ← pre-filled with TODO markers
│   ├── well-architected.md          ← official sources PRE-SEEDED for domain
│   └── llm-anti-patterns.md         ← 5+ AI-specific mistakes to avoid
├── templates/<skill-name>-template.md
└── scripts/check_<noun>.py          ← stdlib-only checker stub

new_skill.py will warn if coverage already exists and ask for confirmation.

Step 3 — Fill All TODOs

Every file created by the scaffold has TODO: markers. Fill them all:

SKILL.md — description (must include "NOT for ..."), triggers (3+, 10+ chars each), tags, inputs, outputs, well-architected-pillars, full body (300+ words), and ## Recommended Workflow (3–7 numbered agent steps)
references/examples.md — real examples with context, problem, solution
references/gotchas.md — non-obvious platform behaviors
references/well-architected.md — WAF notes; official sources are pre-seeded, add usage context
references/llm-anti-patterns.md — 5+ mistakes AI assistants make in this domain: wrong output, why it happens, correct pattern, detection hint
scripts/check_<noun>.py — implement the actual checks (stdlib only)

Read the full file on GitHub · 92 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 92 lines · 0 tokens per session scan A ca458c205617

Subscribe to this mod's changes

new-skill is a command published in the GitHub repository BanibrataChatterjee/AwesomeSalesforceSkills (4 stars, last pushed 6mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 729 tokens. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

new-skill next to 6 commands from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
new-skillBanibrataChatterjee/AwesomeSalesforceSkills	Command	4	6mo ago	Apache-2.0	A	0	Claude Code
checklistgithub/spec-kit	Command	148k	today	MIT	A	13	Claude Code
clarifygithub/spec-kit	Command	148k	today	MIT	A	27	Claude Code
specifygithub/spec-kit	Command	148k	today	MIT	A	13	Claude Code
analyzegithub/spec-kit	Command	148k	today	MIT	A	26	Claude Code
convergegithub/spec-kit	Command	148k	today	MIT	A	35	Claude Code
implementgithub/spec-kit	Command	148k	today	MIT	A	14	Claude Code