feat(browser): byg-et-flow intake/build skill - #2
Closed
simo787c wants to merge 1 commit into
Closed
Conversation
The build-from-scratch skill for agentbase-browser — the intake front half the MCP's guidance.py (mechanics canon) deliberately lacks. - skills/byg-et-flow/SKILL.md — interview → confirm the plan in chat → build → run on a real sample → iterate. Enforces a five-point intake bar before building (process+rules, variants, a real sample input, output+audience, Human-in-the-Loop placement) and the chat-checkpoint discipline (the canvas is invisible in another tab). Hands off to the MCP mechanics: read guide://flow-building, confirm handles with get_node_type, lay the whole graph in one set_flow rather than clobber-prone incremental edits. - skills/byg-et-flow/references/flow-eksempler.md — four Danish flow shapes distilled from guidance.py EXAMPLES + docs relationships.md (document → structured data → spreadsheet; sort a document pile; loop over a list; conditional branching), each pointing at the live example:// resource and get_node_type for exact handles, so tool-schema drift can't reach the skill. RED/GREEN tested: without the skill a fresh agent gathered only a partial intake (missed variants and the approval step); with it, the full five-point intake plus confirm-in-chat/run-on-sample loop. Co-Authored-By: Claude <noreply@anthropic.com> via Dash <dash@syv.ai> Claude-Session: https://claude.ai/code/session_01SYvwyQEa9xsKzsQTwpBuhp
This was referenced Jul 27, 2026
simo787c
marked this pull request as ready for review
July 27, 2026 09:45
Contributor
Author
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What
PR 2 of 4 for
agentbase-browser. Addsbyg-et-flow— the skill that builds a flow from scratch by interviewing the user first. This is the intake front half the MCP'sguidance.py(the mechanics canon) deliberately lacks.Stacked on #1 (base =
feat/agentbase-browser-kom-i-gang) — merge that first.The skill
skills/byg-et-flow/SKILL.md— the loop is interview → confirm the plan in chat → build → run on a real sample → iterate. Two disciplines it enforces:It hands off to the MCP for mechanics (read
guide://flow-building, confirm handles withget_node_type, lay the whole graph in oneset_flowrather than clobber-prone incrementaladd_node/connect_nodes) — it does not reproduce tool schemas, so tool-schema drift can't reach it.skills/byg-et-flow/references/flow-eksempler.md— four Danish flow shapes (document → structured data → spreadsheet; sort a document pile; loop over a list; conditional branching), each distilled fromguidance.pyEXAMPLES + docsrelationships.mdand pointing at the liveexample://resource for the copy-ready graph.Testing
RED/GREEN with fresh subagents on an eager-accountant scenario. Without the skill the agent narrowed to two questions and skipped variants + the approval step; with it, the full five-point intake plus the confirm-in-chat / run-on-real-sample loop.
🤖 Generated with Claude Code
https://claude.ai/code/session_01SYvwyQEa9xsKzsQTwpBuhp