Borrowing it
Nothing to install: this file belongs to sylphiette269/premiere-mcp-editor-cn. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/sylphiette269/premiere-mcp-editor-cn/main/.codex/skills/premiere-skill-first-iteration/SKILL.mdgit clone --depth 1 https://github.com/sylphiette269/premiere-mcp-editor-cnWrote 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.
[](https://agentmods.dev/skills/sylphiette269/premiere-mcp-editor-cn/premiere-skill-first-iteration)<a href="https://agentmods.dev/skills/sylphiette269/premiere-mcp-editor-cn/premiere-skill-first-iteration"><img src="https://agentmods.dev/badge/skills/sylphiette269/premiere-mcp-editor-cn/premiere-skill-first-iteration/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.
<a href="https://agentmods.dev/skills/sylphiette269/premiere-mcp-editor-cn/premiere-skill-first-iteration"><img src="https://agentmods.dev/badge/skills/sylphiette269/premiere-mcp-editor-cn/premiere-skill-first-iteration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00039 | $0.00359 |
| Opus 5 | $0.00019 | $0.00179 |
| Sonnet 5 | $0.00008 | $0.00072 |
| Haiku 4.5 | $0.00004 | $0.00036 |
Grade A, and why
premiere-skill-first-iteration 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 12d 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.
What it actually says
Premiere Skill-First Iteration
Overview
This skill makes the repo capture difficult workflow knowledge before adding more MCP behavior.
When to Use
- The same class of failure keeps repeating
- A DOCX, media, transition, or QA workflow is still ambiguous
- The repo needs a stable local process before another round of MCP changes
Required Loop
- Capture the failing pattern.
- Add or update a repository-local skill.
- Add tests around the clarified behavior.
- Then change MCP code and docs.
Agent Closed-Loop Addendum
When the recurring failure is caused by agent orchestration rather than a single tool bug, capture the workflow rules here before expanding the MCP surface:
- Disable known-bad tool paths explicitly instead of leaving them selectable.
- Require a research gate for style-driven or reference-driven edit tasks.
- Treat write success as provisional until a read-back verifier confirms the result.
- Add an independent critic step before the agent can claim completion.
- Standardize machine-readable error codes so retry logic does not depend on string guessing.
This addendum is the minimum bar for any new closed-loop Premiere agent behavior.
Guardrails
- Do not expand MCP behavior first and explain it later.
- Do not keep workflow rules only in chat context.
- Update the skill when the implementation evolves.
Common Mistakes
- Treating a recurring problem as a one-off
- Fixing code without updating project-local guidance
- Letting docs, skills, and MCP drift apart
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.
- 12d ago First seen · 49 lines · 39 tokens per session scan A be7ceec4eafb
premiere-skill-first-iteration is a skill published in the GitHub repository sylphiette269/premiere-mcp-editor-cn (7 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 359 once invoked, about $0.0002 per session on Opus 5. 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.
Other skills, from other repositories
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…
browser_cdp
A health check for Python code that produces a score, letter grade, and measures of issues such as complexity, duplication, dead code, dependencies, and architecture.
redteam-reverse-detail-pack
Domain routing and boundary guidance for authorized reverse engineering analysis, including decompilation, debugging, protocol reversing, firmware extraction, and deobfuscation. Use when a task belongs to the reverse engineering domain and needs scope, evidence, pivot, or exit criteria.
report-issue-local
File a bug or feature request against this MCP server's own repo. Use for server-specific issues — tool logic, service integrations, config problems, or domain bugs that aren't caused by the framework.
sentry
Sentry error tracking and debugging specialist.
shell-scripting
Shell scripting expert for Bash, POSIX compliance, error handling, and automation.