Total Skills
10
Author Profile: vtphan
Skills published by vtphan with real stars/downloads and source-aware metadata.
Total Stars
0
Total Downloads
0
Skills Performance
Comparison chart based on real stars and downloads signals from source data.
design
0
Stars
0
Downloads
0
execute
0
Stars
0
Downloads
0
intent
0
Stars
0
Downloads
0
plan
0
Stars
0
Downloads
0
review-update
0
Stars
0
Downloads
0
architect
0
Stars
0
Downloads
0
vision
0
Stars
0
Downloads
0
wave-execute
0
Stars
0
Downloads
0
Published Skills
design
Use this ACCORD skill when an approved intent exists and the human lead wants to codesign or revise architecture, boundaries, project commands, verification expectations, and consequential decisions. Triggers include "accord design", "draft the design", "revise architecture", "pivot design", or when implementation learning requires a new design version. This skill uses monotonic draft rounds, promotes an approved draft to docs/accord/design/design.md, updates accord-state.md, then commits and tags after human approval.
Repository SourceNeeds Review
execute
Use this ACCORD skill when canonical intent, design, and plan artifacts exist and the human lead wants the current approved unit implemented. Triggers include "accord execute", "execute the current unit", "implement the approved unit", "build the next unit", or "go ahead" after an approved ACCORD plan. This skill writes code, writes docs/accord/reports/exec-<unit-id>.md using the approved u-NNN-slug ID, updates accord-state.md, then commits and tags after human approval.
Repository SourceNeeds Review
intent
Use this ACCORD skill when the human lead wants to codesign or revise project intent before architecture/design work. Triggers include "accord intent", "draft project intent", "revise intent", "pivot intent", or when a project needs a lightweight approved intent artifact for downstream design and planning. This skill uses monotonic draft rounds, promotes an approved draft to docs/accord/intent/intent.md, updates accord-state.md, then commits and tags after human approval.
Repository SourceNeeds Review
plan
Use this ACCORD skill when approved intent and design artifacts exist and the human lead wants an adaptive implementation plan or a revised plan. Triggers include "accord plan", "draft the plan", "choose the next unit", "revise the plan", or when planning needs to adapt after review. The skill may use monotonic draft rounds, promotes an approved draft to docs/accord/plan/plan.md, updates accord-state.md, then commits and tags after human approval.
Repository SourceNeeds Review
review-update
Use this ACCORD skill after execute has produced an execution report and the human lead wants the work reviewed and the plan updated. Triggers include "accord review-update", "review the executed unit", "update the plan after execution", "close this unit", or "what comes next after execute". This skill verifies execution, writes review/update entries into docs/accord/plan/plan.md by default, updates accord-state.md, then commits and tags after human approval.
Repository SourceNeeds Review
architect
Use this skill at two distinct moments in a VADER project. (Mode = draft) When a vision doc exists and an initial architecture doc is needed before drafting the wave plan. Triggers include phrases like "draft the architecture for this project", "produce an architecture doc and Decision Log from this vision", "design the modules and key interfaces for X", or whenever the user wants the structural decisions for a new project committed to writing before wave planning starts. (Mode = ratify) After the user has reviewed the proposed architecture and decisions, to flip Proposed Decision Log entries to Accepted in one pass. Trigger when the user says "ratify the architecture" or "accept the proposed decisions". Do NOT use for mid-cycle architectural revision — that's handled by `wave-update`'s review subagent. Do NOT use to produce code, scaffolding, or implementation; this skill produces decision documents only.
Repository SourceNeeds Review
vision
Use this skill at two distinct moments in a VADER project. (Mode = draft) When the user has a rough idea for a software product or system and wants help shaping it into a vision document. Triggers include phrases like "I have an idea for X, help me think it through", "shape this into a vision doc", "draft a vision for this", "let's brainstorm this product idea", or whenever the user describes an idea conversationally and asks for help making it concrete enough to plan against. (Mode = pivot) When an existing vision doc needs revision because something learned during execution has invalidated a core part of it. Triggers include phrases like "the vision needs to change because of W3", "we need to pivot — the value hypothesis didn't hold", "update the vision to reflect <core change>", or whenever the user explicitly says "vision pivot". Do NOT use to draft requirements, stories, or features (those live in the wave plan). Do NOT use for cosmetic edits or clarifications that don't change the project's direction (t
Repository SourceNeeds Review
wave-execute
Use this skill when a wave plan exists, the current wave is fully planned (in_progress), and the user wants the wave actually built — code written, tests run, and an execution report produced. Triggers include phrases like "execute the current wave", "build W<N>", "implement the current wave's tasks", "let's do the current wave", "run the wave", or whenever a wave plan is provided and the user wants the tasks in its current wave carried out. Also trigger when the user gestures at next steps ("now build it", "go ahead") *after a successful wave-plan or wave-update* — i.e., the most recent change-log entry's audit verdict was `pass` or `pass-with-findings` and `current_wave` reflects an in-progress, fully-planned wave. Do NOT trigger on "go ahead" after a `blocked-update` (audit verdict `fail`) — re-attempt requires the human to either re-run `wave-execute` for the same current_wave with the explicit recovery path or first run `wave-update` to renegotiate. Do NOT use when no wave plan exists yet (run wave-plan
Repository SourceNeeds Review
wave-plan
Use this skill when a vision doc and a ratified architecture doc exist, and the user wants the initial wave plan drafted. Triggers include phrases like "draft the wave plan from the vision and architecture", "produce the initial wave plan for this project", "what's W1 for this project", "break this into waves with W1 as a walking skeleton", or whenever the upstream vision and architecture artifacts are ready and the next step is committing them into a rolling-wave plan. Do NOT use when no architecture doc exists yet (run `architect draft` first). Do NOT use to revise an existing wave plan — that's `wave-update`. Do NOT use to write code; this skill produces a planning document only.
Repository SourceNeeds Review
wave-update
Use this skill at the end of every wave, after `wave-execute` has produced an execution report. The skill reviews the wave (via a fresh-context subagent), surfaces findings to the human for approval, applies any architectural changes, closes the current wave, and expands the next wave's sketch into full detail. Triggers include phrases like "update the wave plan after W<N>", "close out W<N> and plan W<N+1>", "run the review and update", "what comes next after this wave's execution", or whenever an execution report exists for the current wave and the user is ready to advance the cycle. Also trigger when a vision pivot has just happened and the user wants the wave plan reconciled. Do NOT use when no execution report exists yet (run wave-execute first). Do NOT use to write code. Do NOT use mid-wave; this skill operates at wave boundaries only.
Repository SourceNeeds Review