Skip to content

feat: add help subcommand to /fullsend skill#6

Merged
durandom merged 1 commit into
mainfrom
feat/fullsend-help-subcommand
Jun 11, 2026
Merged

feat: add help subcommand to /fullsend skill#6
durandom merged 1 commit into
mainfrom
feat/fullsend-help-subcommand

Conversation

@durandom

Copy link
Copy Markdown
Member

Summary

  • Adds /fullsend help [topic] subcommand — a context-aware onboarding companion for developers using fullsend agents
  • Dynamically inspects the target repo's .fullsend/ directory to show what's customized (images, skills, env files, policies, prompt overrides)
  • Shows the agent pipeline flow (triage → code → review → fix → retro) with slash commands and trigger labels
  • Links to upstream fullsend-ai/fullsend/docs/ for deep dives — no content replication
  • Supports topic routing: agents, setup, customization to show focused sections

Motivation

The skill currently serves operators (validate, inspect, trigger, debug) but has no onboarding path for developers who want to use fullsend agents. Someone working in rhdh-plugins/boost needs to understand what agents exist, how they chain, and what's customized in their deployment.

Test plan

  • Run /fullsend help — should show pipeline diagram, local deployment summary, and upstream doc links
  • Run /fullsend help agents — should show agent catalog section only
  • Run /fullsend with no args — should list help in the command table

🤖 Generated with Claude Code

Context-aware onboarding companion that shows the agent pipeline,
inspects the local .fullsend/ deployment, and links to upstream docs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
@durandom durandom requested a review from kadel as a code owner June 11, 2026 11:37
Copilot AI review requested due to automatic review settings June 11, 2026 11:37
@durandom durandom merged commit df4890c into main Jun 11, 2026
1 check passed

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds a new /fullsend help [topic] subcommand to the Fullsend skill to provide developer-facing onboarding: explains the agent pipeline, inspects local .fullsend/ customizations, and links to upstream documentation.

Changes:

  • Extended /fullsend skill description and command/routing tables to include the new help subcommand.
  • Added a new references/help.md reference implementing topic-based onboarding content and local deployment inspection guidance.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 6 comments.

File Description
.claude/skills/fullsend/SKILL.md Adds help [topic] to the command table and routes it to the new reference doc.
.claude/skills/fullsend/references/help.md Introduces the help subcommand reference content (pipeline diagram, repo inspection steps, upstream links, topic routing).

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +74 to +76
| **review** | `ready-for-review` label, `/fs-review` | Multi-dimension code review (correctness, security, style, docs) |
| **fix** | Review requests changes, `/fs-fix` | Addresses specific review findings, pushes fix commit |
| **retro** | PR merged/closed, `/fs-retro` | Retrospective on the full workflow — files improvement issues |
Comment on lines +18 to +22
### 1. Resolve the target repo

Follow the repo resolution order from the SKILL.md `<repo_resolution>` section to find the repo with `.fullsend/` configuration.

If in a monorepo (e.g., `rhdh-plugins`), note this — the agent operates at repo level, not workspace level.
#### 4a. Read config.yaml

```bash
cat <repo>/.fullsend/config.yaml
Comment on lines +100 to +104
ls <repo>/.fullsend/customized/harness/*.yaml 2>/dev/null
ls <repo>/.fullsend/customized/agents/*.md 2>/dev/null
ls <repo>/.fullsend/customized/skills/*/SKILL.md 2>/dev/null
ls <repo>/.fullsend/customized/env/*.env 2>/dev/null
ls <repo>/.fullsend/customized/policies/*.yaml 2>/dev/null
Comment on lines +159 to +162
### 5. Upstream docs (topic: `setup` or all)

Present as a linked reference table. Construct URLs as `https://github.com/fullsend-ai/fullsend/blob/main/<path>`.

Comment on lines +149 to +157
#### 4e. Custom env files

For each `.env` in `customized/env/`, show what it sets:

```
### Custom Env Files
- rhdh-toolchain.env — sets COREPACK_HOME=/tmp/corepack (writable dir for corepack)
- yarn-proxy.env — maps HTTP_PROXY → YARN_HTTP_PROXY (yarn ignores standard proxy vars)
```
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants